About us
Publications
Home
Publications from 2020 and before are not direct results of the SFI MediaFutures, but are key results from our team members working on related topics in MediaFutures.
2025
Huiling You; Samia Touileb; Lilja Øvrelid; Erik Velldal
Event-based evaluation of abstractive news summarization Conference
ACL Conference, 2025.
BibTeX | Tags: WP5: Norwegian Language Technologies | Links:
@conference{eventbased25,
title = {Event-based evaluation of abstractive news summarization},
author = {Huiling You and Samia Touileb and Lilja Øvrelid and Erik Velldal},
url = {https://mediafutures.no/63_event_based_evaluation_of_a/},
year = {2025},
date = {2025-06-02},
booktitle = {ACL Conference},
keywords = {WP5: Norwegian Language Technologies},
pubstate = {published},
tppubtype = {conference}
}
Martin Salterød Sjåvik; Samia Touileb
Ableism, Ageism, Gender, and Nationality bias in Norwegian and Multilingual Language Models Workshop
2025.
Abstract | BibTeX | Tags: WP5: Norwegian Language Technologies | Links:
@workshop{ableism25,
title = {Ableism, Ageism, Gender, and Nationality bias in Norwegian and Multilingual Language Models},
author = {Martin Salterød Sjåvik and Samia Touileb},
url = {https://mediafutures.no/ableism_ageism_gender_and_nationality_bias_in_norwegian_and_multilingual_language_models/},
year = {2025},
date = {2025-06-02},
urldate = {2025-06-02},
journal = {Workshop on Gender Bias in Natural Language Processing},
issue = {ACL Conference},
abstract = {We investigate biases related to ageism, ableism, nationality, and gender in four Norwegian and two multilingual language models. Our methodology involves using a set of templates constructed around stimuli and attributes relevant to these categories. We use statistical and predictive evaluation methods, including Kendall’s Tau correlation and dependent variable prediction rates, to assess model behaviour and output bias. Our findings indicate that models frequently associate older individuals, people with disabilities, and poorer countries with negative attributes, potentially reinforcing harmful stereotypes. However, most tested models appear to handle gender-related biases more effectively. Our findings indicate a correlation between the sentiment of the input and that of the output.},
keywords = {WP5: Norwegian Language Technologies},
pubstate = {published},
tppubtype = {workshop}
}
We investigate biases related to ageism, ableism, nationality, and gender in four Norwegian and two multilingual language models. Our methodology involves using a set of templates constructed around stimuli and attributes relevant to these categories. We use statistical and predictive evaluation methods, including Kendall’s Tau correlation and dependent variable prediction rates, to assess model behaviour and output bias. Our findings indicate that models frequently associate older individuals, people with disabilities, and poorer countries with negative attributes, potentially reinforcing harmful stereotypes. However, most tested models appear to handle gender-related biases more effectively. Our findings indicate a correlation between the sentiment of the input and that of the output.
Jia Hua Jeng; Gloria Anne Babile Kasangu; Alain D. Starke; Khadiga Seddik; Christoph Trattner
The role of GPT as an adaptive technology in climate change journalism Conference
UMAP 2025, 2025.
Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links:
@conference{roleofGPT25,
title = {The role of GPT as an adaptive technology in climate change journalism},
author = {Jia Hua Jeng and Gloria Anne Babile Kasangu and Alain D. Starke and Khadiga Seddik and Christoph Trattner},
url = {https://mediafutures.no/umap2025-0401_small/},
year = {2025},
date = {2025-03-28},
booktitle = {UMAP 2025},
abstract = {Recent advancements in Large Language Models (LLMs), such as GPT-4o, have enabled automated content generation and adaptation, including summaries of news articles. To date, LLM use in a journalism context has been understudied, but can potentially address challenges of selective exposure and polarization by adapting content to end users. This study used a one-shot recommender platform to test whether LLM-generated news summaries were evaluated more positively than `standard' 50-word news article previews. Moreover, using climate change news from the Washington Post, we also compared the influence of different `emotional reframing' strategies to rewrite texts and their impact on the environmental behavioral intentions of end users. We used a 2 (between: Summary vs. 50-word previews) x 3 (within: fear, fear-hope or neutral reframing) research design. Participants (N = 300) were first asked to read news articles in our interface and to choose a preferred news article, while later performing an in-depth evaluation task on the usability (e.g., clarity) and trustworthiness of different framing strategies. Results showed that evaluations of summaries, while being positive, were not significantly better than those of previews. We did, however, observe that a fear-hope reframing strategy of a news article, when paired with a GPT-generated summary, led to higher pro-environmental intentions compared to neutral framing. We discuss the potential benefits of this technology.},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {conference}
}
Recent advancements in Large Language Models (LLMs), such as GPT-4o, have enabled automated content generation and adaptation, including summaries of news articles. To date, LLM use in a journalism context has been understudied, but can potentially address challenges of selective exposure and polarization by adapting content to end users. This study used a one-shot recommender platform to test whether LLM-generated news summaries were evaluated more positively than `standard' 50-word news article previews. Moreover, using climate change news from the Washington Post, we also compared the influence of different `emotional reframing' strategies to rewrite texts and their impact on the environmental behavioral intentions of end users. We used a 2 (between: Summary vs. 50-word previews) x 3 (within: fear, fear-hope or neutral reframing) research design. Participants (N = 300) were first asked to read news articles in our interface and to choose a preferred news article, while later performing an in-depth evaluation task on the usability (e.g., clarity) and trustworthiness of different framing strategies. Results showed that evaluations of summaries, while being positive, were not significantly better than those of previews. We did, however, observe that a fear-hope reframing strategy of a news article, when paired with a GPT-generated summary, led to higher pro-environmental intentions compared to neutral framing. We discuss the potential benefits of this technology.
Florence Walker; Irene Costera Meijer; Enrico Motta
Grounding and Anchoring: Success Factors for Academia-Industry Collaboration Working paper
2025.
Abstract | BibTeX | Tags: | Links:
@workingpaper{nokey,
title = {Grounding and Anchoring: Success Factors for Academia-Industry Collaboration},
author = {Florence Walker and Irene Costera Meijer and Enrico Motta},
url = {https://mediafutures.no/grounding-anchoring-aic-inline-figures-3/},
year = {2025},
date = {2025-03-14},
urldate = {2025-03-14},
abstract = {This paper integrates a top-down analysis of the existing literature on academia-industry collaboration (AIC) with a bottom-up qualitative study consisting of 16 anonymised interviews. From a variety of academic and industry sources we identified three dominant discourses that are frequently drawn upon. These often-repeated statements, while partially true, act to obscure considerably complexity and nuance. In an effort to expand existing AIC discourse, we introduce two key concepts: grounding and anchoring. These can take place in an organisational or a personal context. An AIC project is personally grounded, when individuals involved in the project feel that the work is meaningful to them, that it is aligned with their wider values and is making a difference to the world. Analogously, organisational grounding indicates that a project is consistent with the culture and values of the organisation. An AIC project is personally anchored when the people responsible for it feel a strong sense of ownership and agency towards the project. Organisational anchoring indicates that a project is fully supported within the organisation, in particular by the relevant managers and executives. When a project is sufficiently grounded and anchored, success and the personal satisfaction of the people involved in the activity are more likely to follow.
Keywords
},
keywords = {},
pubstate = {published},
tppubtype = {workingpaper}
}
This paper integrates a top-down analysis of the existing literature on academia-industry collaboration (AIC) with a bottom-up qualitative study consisting of 16 anonymised interviews. From a variety of academic and industry sources we identified three dominant discourses that are frequently drawn upon. These often-repeated statements, while partially true, act to obscure considerably complexity and nuance. In an effort to expand existing AIC discourse, we introduce two key concepts: grounding and anchoring. These can take place in an organisational or a personal context. An AIC project is personally grounded, when individuals involved in the project feel that the work is meaningful to them, that it is aligned with their wider values and is making a difference to the world. Analogously, organisational grounding indicates that a project is consistent with the culture and values of the organisation. An AIC project is personally anchored when the people responsible for it feel a strong sense of ownership and agency towards the project. Organisational anchoring indicates that a project is fully supported within the organisation, in particular by the relevant managers and executives. When a project is sufficiently grounded and anchored, success and the personal satisfaction of the people involved in the activity are more likely to follow.
Keywords
Keywords
Peter Andrews; Njål Borch; Morten Fjeld
AiModerator: A Co-Pilot for Hyper-Contextualization in Political Debate Video Conference
Intelligent User Interfaces (IUI) 2025, 2025.
Abstract | BibTeX | Tags: WP4: Media Content Interaction and Accessibility | Links:
@conference{AIMod24,
title = {AiModerator: A Co-Pilot for Hyper-Contextualization in Political Debate Video},
author = {Peter Andrews and Njål Borch and Morten Fjeld},
url = {https://mediafutures.no/iui25-78/},
year = {2025},
date = {2025-03-01},
booktitle = {Intelligent User Interfaces (IUI) 2025},
abstract = {Political debates are essential in political discourse for democratic societies. Advancements in technology have significantly transformed the structure of political debates, the ways in which politicians communicate, and the platforms through which audiences engage with them. Originally a forum for improving understanding, political debates have increasingly favored theatrics over substance, risking young adult disengagement. To bring substance back to this medium we developed AiModerator, a political debate co-pilot acting as a Multimodal Conversational Agent (MCA). AiModerator aims to promote engagement while improving understanding by analyzing video content to provide contextually relevant information. This consolidated information facilitates understanding while keeping users synchronized with the debate viewing experience. Our system builds upon multimodal techniques, integrating computer vision and large language models to demonstrate ways of improving content delivery and engagement. AiModerator's backend system extracts events from identified speech data, allowing the user to interact with these events through a touch interface on an iPad application. We address three key topics: evaluating young adults' engagement, satisfaction, and preference compared to traditional second screening, and determining whether AiModerator can improve subjective understanding. To evaluate these measures we conducted a mixed-method evaluation (n=20) within-group design A-B study. Our analysis found AiModerator excelled in promoting engagement and satisfaction while delivering clear, contextually relevant information to the user which improved their understanding of debate topics more than the second screening mode. Our qualitative analysis offers broader insights, particularly in terms of a trade-off between automation and information consolidation versus autonomy and control.},
keywords = {WP4: Media Content Interaction and Accessibility},
pubstate = {published},
tppubtype = {conference}
}
Political debates are essential in political discourse for democratic societies. Advancements in technology have significantly transformed the structure of political debates, the ways in which politicians communicate, and the platforms through which audiences engage with them. Originally a forum for improving understanding, political debates have increasingly favored theatrics over substance, risking young adult disengagement. To bring substance back to this medium we developed AiModerator, a political debate co-pilot acting as a Multimodal Conversational Agent (MCA). AiModerator aims to promote engagement while improving understanding by analyzing video content to provide contextually relevant information. This consolidated information facilitates understanding while keeping users synchronized with the debate viewing experience. Our system builds upon multimodal techniques, integrating computer vision and large language models to demonstrate ways of improving content delivery and engagement. AiModerator's backend system extracts events from identified speech data, allowing the user to interact with these events through a touch interface on an iPad application. We address three key topics: evaluating young adults' engagement, satisfaction, and preference compared to traditional second screening, and determining whether AiModerator can improve subjective understanding. To evaluate these measures we conducted a mixed-method evaluation (n=20) within-group design A-B study. Our analysis found AiModerator excelled in promoting engagement and satisfaction while delivering clear, contextually relevant information to the user which improved their understanding of debate topics more than the second screening mode. Our qualitative analysis offers broader insights, particularly in terms of a trade-off between automation and information consolidation versus autonomy and control.
Vinay Setty; Adam James Becker
Annotation Tool and Dataset for Fact-Checking Podcasts Conference
The Web Conference 2025, 2025.
Abstract | BibTeX | Tags: | Links:
@conference{annot25,
title = {Annotation Tool and Dataset for Fact-Checking Podcasts},
author = {Vinay Setty and Adam James Becker},
url = {https://mediafutures.no/2502-01402v1/},
year = {2025},
date = {2025-02-03},
booktitle = {The Web Conference 2025},
abstract = {Podcasts are a popular medium on the web, featuring diverse and multilingual content that often includes unverified claims. Fact-checking podcasts is a challenging task, requiring transcription, annotation, and claim verification, all while preserving the contextual details of spoken content. Our tool offers a novel approach to tackle these challenges by enabling real-time annotation of podcasts during playback. This unique capability allows users to listen to the podcast and annotate key elements, such as check-worthy claims, claim spans, and contextual errors, simultaneously. By integrating advanced transcription models like OpenAI's Whisper and leveraging crowdsourced annotations, we create high-quality datasets to fine-tune multilingual transformer models such as XLM-RoBERTa for tasks like claim detection and stance classification. Furthermore, we release the annotated podcast transcripts and sample annotations with preliminary experiments.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Podcasts are a popular medium on the web, featuring diverse and multilingual content that often includes unverified claims. Fact-checking podcasts is a challenging task, requiring transcription, annotation, and claim verification, all while preserving the contextual details of spoken content. Our tool offers a novel approach to tackle these challenges by enabling real-time annotation of podcasts during playback. This unique capability allows users to listen to the podcast and annotate key elements, such as check-worthy claims, claim spans, and contextual errors, simultaneously. By integrating advanced transcription models like OpenAI's Whisper and leveraging crowdsourced annotations, we create high-quality datasets to fine-tune multilingual transformer models such as XLM-RoBERTa for tasks like claim detection and stance classification. Furthermore, we release the annotated podcast transcripts and sample annotations with preliminary experiments.
Anastasiia Klimashevskaia; Snorre Alvsvåg; Christoph Trattner; Alain D. Starke; Astrid Tessem; Dietmar Jannach
Evaluating Sequential Recommendations in the Wild: A Case Study on Offline Accuracy, Click Rates, and Consumption Conference
ECIR 2025 conference, 2025.
Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links:
@conference{seque25,
title = {Evaluating Sequential Recommendations in the Wild: A Case Study on Offline Accuracy, Click Rates, and Consumption},
author = {Anastasiia Klimashevskaia and Snorre Alvsvåg and Christoph Trattner and Alain D. Starke and Astrid Tessem and Dietmar Jannach},
url = {https://mediafutures.no/anastasiia__snorre___ecir_2025_camera_ready_ver_2-1/},
year = {2025},
date = {2025-02-01},
booktitle = {ECIR 2025 conference},
abstract = {Sequential recommendation problems have received increased research interest in recent years. Our knowledge about the effectiveness of sequential algorithms in practice is however limited. In this paper, we report on the outcomes of an A/B test on a video and movie streaming platform, where we benchmarked a sequential model against a non-sequential, personalized recommendation model, as well as a popularity-based baseline. Contrary to what we had expected from a preceding offline experiment, we observed that the popularity-based and the non-sequential models led to the highest click-through rates. However, in terms of the adoption of the recommendations, the sequential model was the most successful one in terms of viewing times. While our work points out the effectiveness of sequential models in practice, it also reminds us about important open challenges regarding (a) the sometimes limited predictive power of classic offline evaluations and (b) the dangers of optimizing recommendation models for click-through-rates.},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {conference}
}
Sequential recommendation problems have received increased research interest in recent years. Our knowledge about the effectiveness of sequential algorithms in practice is however limited. In this paper, we report on the outcomes of an A/B test on a video and movie streaming platform, where we benchmarked a sequential model against a non-sequential, personalized recommendation model, as well as a popularity-based baseline. Contrary to what we had expected from a preceding offline experiment, we observed that the popularity-based and the non-sequential models led to the highest click-through rates. However, in terms of the adoption of the recommendations, the sequential model was the most successful one in terms of viewing times. While our work points out the effectiveness of sequential models in practice, it also reminds us about important open challenges regarding (a) the sometimes limited predictive power of classic offline evaluations and (b) the dangers of optimizing recommendation models for click-through-rates.
Marianne Borchgrevink-Brækhus
Understanding news experience: The resonance between content, practices, and situatedness in everyday life Journal Article
In: Journalism, 2025.
Abstract | BibTeX | Tags: WP1: Understanding Media Experiences | Links:
@article{understanding25,
title = {Understanding news experience: The resonance between content, practices, and situatedness in everyday life},
author = {Marianne Borchgrevink-Brækhus},
url = {https://mediafutures.no/borchgrevink-braekhus-2025-understanding-news-experience-the-resonance-between-content-practices-and-situatedness-in/},
year = {2025},
date = {2025-01-21},
urldate = {2024-12-21},
journal = {Journalism},
abstract = {People relate to news in highly complex ways. Research on news audiences has identified how content reception, user practices, and spatiotemporal contexts influence relations to news. This study aims to see these dimensions as connected, emphasizing the significance of understanding how news content, practices, and people’s situatedness resonate in the context of everyday life and how this resonance reflects personal identity. Conceptually, the paper employs the concept of news experience as an analytical lens to understand the multilayered nature of how people relate to news. Empirically, six distinct forms of news experience are identified, all in which content, practices, and situatedness resonate differently: Reassurance, control, connection, relaxation, diversion, and stress. Drawing on a Norwegian three-step data collection, including recurring interviews, news diaries, data donations, and video-ethnography from the same informants, the article methodologically contributes to a more profound understanding of the dynamics involved in various forms of news experience.},
keywords = {WP1: Understanding Media Experiences},
pubstate = {published},
tppubtype = {article}
}
People relate to news in highly complex ways. Research on news audiences has identified how content reception, user practices, and spatiotemporal contexts influence relations to news. This study aims to see these dimensions as connected, emphasizing the significance of understanding how news content, practices, and people’s situatedness resonate in the context of everyday life and how this resonance reflects personal identity. Conceptually, the paper employs the concept of news experience as an analytical lens to understand the multilayered nature of how people relate to news. Empirically, six distinct forms of news experience are identified, all in which content, practices, and situatedness resonate differently: Reassurance, control, connection, relaxation, diversion, and stress. Drawing on a Norwegian three-step data collection, including recurring interviews, news diaries, data donations, and video-ethnography from the same informants, the article methodologically contributes to a more profound understanding of the dynamics involved in various forms of news experience.
Alain D. Starke; Sanne Vrijenhoek; Lien Michiels; Johannes Kruse; Nava Tintarev
Report on NORMalize: The Second Workshop on the Normative Design and Evaluation of Recommender Systems Workshop Forthcoming
Forthcoming.
Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links:
@workshop{Report_Normalize25,
title = {Report on NORMalize: The Second Workshop on the Normative Design and Evaluation of Recommender Systems},
author = {Alain D. Starke and Sanne Vrijenhoek and Lien Michiels and Johannes Kruse and Nava Tintarev},
url = {https://mediafutures.no/preface-2/},
year = {2025},
date = {2025-01-19},
issue = {CEUR Vol-3898},
abstract = {Recommender systems are among the most widely used applications of artificial intelligence. Because of their widespread use, it is important that practitioners and researchers think about the impact they may have on users, society, and other stakeholders. To that effect, the NORMalize workshop seeks to introduce normative thinking, to consider the norms and values that underpin recommender systems in the recommender systems community. The objective of NORMalize is to bring together a growing community of researchers and practitioners across disciplines who want to think about the norms and values that should be considered in the design and evaluation of recommender systems, and further educate them on how to reflect on, prioritise, and operationalise such norms and values. This document is a report on the second NORMalize workshop, co-located with ACM RecSys ’24 in Bari, Italy.},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {forthcoming},
tppubtype = {workshop}
}
Recommender systems are among the most widely used applications of artificial intelligence. Because of their widespread use, it is important that practitioners and researchers think about the impact they may have on users, society, and other stakeholders. To that effect, the NORMalize workshop seeks to introduce normative thinking, to consider the norms and values that underpin recommender systems in the recommender systems community. The objective of NORMalize is to bring together a growing community of researchers and practitioners across disciplines who want to think about the norms and values that should be considered in the design and evaluation of recommender systems, and further educate them on how to reflect on, prioritise, and operationalise such norms and values. This document is a report on the second NORMalize workshop, co-located with ACM RecSys ’24 in Bari, Italy.
Huiling You; Samia Touileb; Erik Velldal; Lilja Øvrelid
NorEventGen: generative event extraction from Norwegian news Conference
(NoDaLiDa/Baltic-HLT 2025, 2025.
Abstract | BibTeX | Tags: WP5: Norwegian Language Technologies | Links:
@conference{norevent25,
title = {NorEventGen: generative event extraction from Norwegian news},
author = {Huiling You and Samia Touileb and Erik Velldal and Lilja Øvrelid},
url = {https://mediafutures.no/2025_nodalida_1_79/},
year = {2025},
date = {2025-01-13},
booktitle = {(NoDaLiDa/Baltic-HLT 2025},
abstract = {In this work, we approach event extraction from Norwegian news text using a
generation-based approach, which formulates the task as text-to-structure generation. We present experiments assessing the
effect of different modeling configurations
and provide an analysis of the model predictions and typical system errors. Finally,
we apply our system to a large corpus of
raw news texts and analyze the resulting
distribution of event structures in a fairly
representative snap-shot of the Norwegian
news landscape.},
keywords = {WP5: Norwegian Language Technologies},
pubstate = {published},
tppubtype = {conference}
}
In this work, we approach event extraction from Norwegian news text using a
generation-based approach, which formulates the task as text-to-structure generation. We present experiments assessing the
effect of different modeling configurations
and provide an analysis of the model predictions and typical system errors. Finally,
we apply our system to a large corpus of
raw news texts and analyze the resulting
distribution of event structures in a fairly
representative snap-shot of the Norwegian
news landscape.
generation-based approach, which formulates the task as text-to-structure generation. We present experiments assessing the
effect of different modeling configurations
and provide an analysis of the model predictions and typical system errors. Finally,
we apply our system to a large corpus of
raw news texts and analyze the resulting
distribution of event structures in a fairly
representative snap-shot of the Norwegian
news landscape.
Samia Touileb; Vladislav Mikhailov, Marie Kroka, Lilja Øvrelid, Erik Velldal
Benchmarking Abstractive Summarisation: A dataset of human-authored summaries of Norwegian news articles Conference
NoDaLiDa2025, 2025.
BibTeX | Tags: WP5: Norwegian Language Technologies | Links:
@conference{benchmark25,
title = {Benchmarking Abstractive Summarisation: A dataset of human-authored summaries of Norwegian news articles},
author = {Samia Touileb and Vladislav Mikhailov, Marie Kroka, Lilja Øvrelid, Erik Velldal},
url = {https://mediafutures.no/2501-07718v1/},
year = {2025},
date = {2025-01-13},
urldate = {2025-01-13},
booktitle = {NoDaLiDa2025},
keywords = {WP5: Norwegian Language Technologies},
pubstate = {published},
tppubtype = {conference}
}
Adane Nega Tarekegn; Bjørnar Tessem; Fazle Rabbi
A New Cluster Validation Index based on Stability Analysis Conference
ICPRAM 2025, 2025.
Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links:
@conference{clustervalidtio25,
title = {A New Cluster Validation Index based on Stability Analysis},
author = {Adane Nega Tarekegn and Bjørnar Tessem and Fazle Rabbi},
url = {https://mediafutures.no/133091/},
year = {2025},
date = {2025-01-01},
booktitle = {ICPRAM 2025},
journal = {ICPRAM 2025},
abstract = {Clustering is a frequently employed technique across various domains, including anomaly detection, recommender systems, video analysis, and natural language processing. Despite its broad application, validating clustering results has become one of the main challenges in cluster analysis. This can be due to factors such as the subjective nature of clustering evaluation, lack of ground truth in many real-world datasets, and sensitivity of evaluation metrics to different cluster shapes and algorithms. While there is extensive literature work in this area, developing an evaluation method that is both objective and quantitative is still challenging task requiring more effort. In this study, we proposed a new Clustering Stability Assessment Index (CSAI) that can provide a unified and quantitative approach to measure the quality and consistency of clustering solutions. The proposed CSAI validation index leverages a data resampling approach and prediction analysis to assess clustering stabil},
keywords = {WP3: Media Content Production and Analysis},
pubstate = {published},
tppubtype = {conference}
}
Clustering is a frequently employed technique across various domains, including anomaly detection, recommender systems, video analysis, and natural language processing. Despite its broad application, validating clustering results has become one of the main challenges in cluster analysis. This can be due to factors such as the subjective nature of clustering evaluation, lack of ground truth in many real-world datasets, and sensitivity of evaluation metrics to different cluster shapes and algorithms. While there is extensive literature work in this area, developing an evaluation method that is both objective and quantitative is still challenging task requiring more effort. In this study, we proposed a new Clustering Stability Assessment Index (CSAI) that can provide a unified and quantitative approach to measure the quality and consistency of clustering solutions. The proposed CSAI validation index leverages a data resampling approach and prediction analysis to assess clustering stabil
2024
Khadiga Seddik
Exploring the Ethical Challenges of AI and Recommender Systems in the Democratic Public Sphere Conference
NIKT, 2024.
Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links:
@conference{democratpu24,
title = {Exploring the Ethical Challenges of AI and Recommender Systems in the Democratic Public Sphere},
author = {Khadiga Seddik},
url = {https://mediafutures.no/camera-ready-3/},
year = {2024},
date = {2024-11-25},
urldate = {2024-11-25},
booktitle = {NIKT},
abstract = {The rapid integration of Artificial Intelligence (AI) and Recommender Systems (RSs) into digital platforms has brought both opportunities and ethical concerns. These systems, designed to personalize content and optimize user engagement, have the potential to enhance how individuals navigate information online. However, this paper shifts the focus to the ethical complexities inherent in such systems, particularly the practice of nudging, where subtle algorithmic suggestions influence user behavior without explicit awareness. Issues like misinformation, algorithmic bias, privacy protection, and diminished content diversity raise important questions about the role of AI in shaping public discourse and decision-making processes. Rather than viewing these systems solely as tools for convenience, the paper challenges the reader to consider the deeper implications of AI-driven recommendations on democratic engagement. By examining how these technologies can quietly influence decisions and reduce exposure to different perspectives, it calls for a reevaluation of the ethical priorities in AI and RSs design. The paper calls for creating a digital space that promotes independence, fairness, and openness, making sure AI is used responsibly to support democratic values and protect user rights.},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {conference}
}
The rapid integration of Artificial Intelligence (AI) and Recommender Systems (RSs) into digital platforms has brought both opportunities and ethical concerns. These systems, designed to personalize content and optimize user engagement, have the potential to enhance how individuals navigate information online. However, this paper shifts the focus to the ethical complexities inherent in such systems, particularly the practice of nudging, where subtle algorithmic suggestions influence user behavior without explicit awareness. Issues like misinformation, algorithmic bias, privacy protection, and diminished content diversity raise important questions about the role of AI in shaping public discourse and decision-making processes. Rather than viewing these systems solely as tools for convenience, the paper challenges the reader to consider the deeper implications of AI-driven recommendations on democratic engagement. By examining how these technologies can quietly influence decisions and reduce exposure to different perspectives, it calls for a reevaluation of the ethical priorities in AI and RSs design. The paper calls for creating a digital space that promotes independence, fairness, and openness, making sure AI is used responsibly to support democratic values and protect user rights.
Ingar M Arntzen; Njål Borch; Anders Andersen
Control-driven Media. A unifying model for consistent, cross-platform multimedia experiences Journal Article
In: FTC 2024 International Journal of Advanced Computer Science and Applications (IJACSA), 2024.
Abstract | BibTeX | Tags: WP4: Media Content Interaction and Accessibility | Links:
@article{controldrivingar24,
title = {Control-driven Media. A unifying model for consistent, cross-platform multimedia experiences},
author = {Ingar M Arntzen and Njål Borch and Anders Andersen},
url = {https://mediafutures.no/preprint_cdm/},
year = {2024},
date = {2024-11-24},
journal = {FTC 2024 International Journal of Advanced Computer Science and Applications (IJACSA)},
abstract = {Targeting a diverse consumer base, many media providers offer complementary products on different platforms. Online sports coverage for instance, may include professionally produced audio and video channels, as well as Web pages and native apps offering live statistics, maps, data visualizations, social commentary and more. Many consumers are also engaging in parallel usage, setting up streaming products and interactive interfaces on available screens, laptops and handheld devices. This ability to combine products holds great promise, yet, with no coordination, cross-platform user experiences often appear inconsistent and disconnected.
We present emph{Control-driven Media (CdM)}, a new media model adding support for coordination and consistency across interfaces, devices, products and platforms, while also remaining compatible with existing services, technologies and workflows. CdM promotes online media control as an independent resource type in multimedia systems. With control as a driving force, CdM offers a highly flexible model, opening up for further innovations in automation, personalization, multi-device support, collaboration and time-driven visualization. Furthermore, CdM bridges the gap between continuous media and Web/native apps, allowing the combined powers of these platforms to be seamlessly exploited as parts of a single, consistent user experience.
CdM is supported by extensive research in time-dependent, multi-device, data-driven media experiences. In particular, State Trajectory, a unifying concept for online, timeline-consistent media control, has recently been proposed as a generic solution for media control in CdM. This paper makes the case for CdM, bringing a significant potential to the attention of research and industry.},
keywords = {WP4: Media Content Interaction and Accessibility},
pubstate = {published},
tppubtype = {article}
}
Targeting a diverse consumer base, many media providers offer complementary products on different platforms. Online sports coverage for instance, may include professionally produced audio and video channels, as well as Web pages and native apps offering live statistics, maps, data visualizations, social commentary and more. Many consumers are also engaging in parallel usage, setting up streaming products and interactive interfaces on available screens, laptops and handheld devices. This ability to combine products holds great promise, yet, with no coordination, cross-platform user experiences often appear inconsistent and disconnected.
We present emph{Control-driven Media (CdM)}, a new media model adding support for coordination and consistency across interfaces, devices, products and platforms, while also remaining compatible with existing services, technologies and workflows. CdM promotes online media control as an independent resource type in multimedia systems. With control as a driving force, CdM offers a highly flexible model, opening up for further innovations in automation, personalization, multi-device support, collaboration and time-driven visualization. Furthermore, CdM bridges the gap between continuous media and Web/native apps, allowing the combined powers of these platforms to be seamlessly exploited as parts of a single, consistent user experience.
CdM is supported by extensive research in time-dependent, multi-device, data-driven media experiences. In particular, State Trajectory, a unifying concept for online, timeline-consistent media control, has recently been proposed as a generic solution for media control in CdM. This paper makes the case for CdM, bringing a significant potential to the attention of research and industry.
We present emph{Control-driven Media (CdM)}, a new media model adding support for coordination and consistency across interfaces, devices, products and platforms, while also remaining compatible with existing services, technologies and workflows. CdM promotes online media control as an independent resource type in multimedia systems. With control as a driving force, CdM offers a highly flexible model, opening up for further innovations in automation, personalization, multi-device support, collaboration and time-driven visualization. Furthermore, CdM bridges the gap between continuous media and Web/native apps, allowing the combined powers of these platforms to be seamlessly exploited as parts of a single, consistent user experience.
CdM is supported by extensive research in time-dependent, multi-device, data-driven media experiences. In particular, State Trajectory, a unifying concept for online, timeline-consistent media control, has recently been proposed as a generic solution for media control in CdM. This paper makes the case for CdM, bringing a significant potential to the attention of research and industry.
Étienne Simon; Helene Olsen; Huiling You; Samia Touileb; Lilja Øvrelid; Erik Velldal
Generative Approaches to Event Extraction: Survey and Outlook Proceedings
2024.
Abstract | BibTeX | Tags: | Links:
@proceedings{genapproacheseven24,
title = {Generative Approaches to Event Extraction: Survey and Outlook},
author = {Étienne Simon and Helene Olsen and Huiling You and Samia Touileb and Lilja Øvrelid and Erik Velldal},
url = {https://mediafutures.no/2024-futured-1-7/},
year = {2024},
date = {2024-11-15},
issue = {ACL Anthology},
abstract = {This paper aims to map out the current landscape of generative approaches to the task of
event extraction. In surveying the emerging
literature on the topic, we identify the distinctive properties of existing studies and catalogue
them to build a comprehensive view of the various techniques employed. Finally, looking
ahead, we argue for a new generative formulation of event extraction, allowing for a better
fit between methodology and task – a proposal
that could also pertain to many other traditional
NLP tasks currently based on annotations of
text-spans.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
This paper aims to map out the current landscape of generative approaches to the task of
event extraction. In surveying the emerging
literature on the topic, we identify the distinctive properties of existing studies and catalogue
them to build a comprehensive view of the various techniques employed. Finally, looking
ahead, we argue for a new generative formulation of event extraction, allowing for a better
fit between methodology and task – a proposal
that could also pertain to many other traditional
NLP tasks currently based on annotations of
text-spans.
event extraction. In surveying the emerging
literature on the topic, we identify the distinctive properties of existing studies and catalogue
them to build a comprehensive view of the various techniques employed. Finally, looking
ahead, we argue for a new generative formulation of event extraction, allowing for a better
fit between methodology and task – a proposal
that could also pertain to many other traditional
NLP tasks currently based on annotations of
text-spans.
Sohail Ahmed Khan; Laurence Dierickx; Jan-Gunnar Furuly; Henrik Brattli Vold; Rano Tahseen; Carl-Gustav Linden; Duc-Tien Dang-Nguyen
Debunking War Information Disorder: A Case Study in Assessing the Use of Multimedia Verification Tools Journal Article
In: Journal of the Association for Information Science and Technology, 2024.
Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links:
@article{warinfo24,
title = {Debunking War Information Disorder: A Case Study in Assessing the Use of Multimedia Verification Tools},
author = {Sohail Ahmed Khan and Laurence Dierickx and Jan-Gunnar Furuly and Henrik Brattli Vold and Rano Tahseen and Carl-Gustav Linden and Duc-Tien Dang-Nguyen},
url = {https://mediafutures.no/jasist_verifyingwarconflict-compressed/},
year = {2024},
date = {2024-11-11},
urldate = {2024-11-11},
journal = {Journal of the Association for Information Science and Technology},
abstract = {This paper investigates the use of multimedia verification, in particular, computational tools and Open-source Intelligence (OSINT) methods, for verifying online multimedia content in the context of the ongoing wars in Ukraine and Gaza. Our study examines the workflows and tools used by several fact-checkers and journalists working at Faktisk, a Norwegian fact-checking organisation. Our study showcases the effectiveness of diverse resources, including AI tools, geolocation tools, internet archives, and social media monitoring platforms, in enabling journalists and fact-checkers to efficiently process and corroborate evidence, ensuring the dissemination of accurate information. This research provides an in-depth analysis of the role of computational tools and OSINT methods for multimedia verification. It also underscores the potentials of currently available technology, and highlights its limitations while providing guidance for future development of digital multimedia verification tools and frameworks.},
keywords = {WP3: Media Content Production and Analysis},
pubstate = {published},
tppubtype = {article}
}
This paper investigates the use of multimedia verification, in particular, computational tools and Open-source Intelligence (OSINT) methods, for verifying online multimedia content in the context of the ongoing wars in Ukraine and Gaza. Our study examines the workflows and tools used by several fact-checkers and journalists working at Faktisk, a Norwegian fact-checking organisation. Our study showcases the effectiveness of diverse resources, including AI tools, geolocation tools, internet archives, and social media monitoring platforms, in enabling journalists and fact-checkers to efficiently process and corroborate evidence, ensuring the dissemination of accurate information. This research provides an in-depth analysis of the role of computational tools and OSINT methods for multimedia verification. It also underscores the potentials of currently available technology, and highlights its limitations while providing guidance for future development of digital multimedia verification tools and frameworks.
Bilal Mahmood; Mehdi Elahi; Samia Touileb; Lubos Steskal
Can Large Language Models Support Editors Pick Related News Articles? Conference
NIKT 2024, 2024.
BibTeX | Tags: WP5: Norwegian Language Technologies | Links:
@conference{canlarge24,
title = {Can Large Language Models Support Editors Pick Related News Articles?},
author = {Bilal Mahmood and Mehdi Elahi and Samia Touileb and Lubos Steskal},
url = {https://mediafutures.no/can_large_language_models_support_editors_pick_related_news_articles____nik_2024-1/},
year = {2024},
date = {2024-11-05},
urldate = {2024-11-05},
booktitle = {NIKT 2024},
keywords = {WP5: Norwegian Language Technologies},
pubstate = {published},
tppubtype = {conference}
}
Bilal Mahmood; Mehdi Elahi; Fahrhad Vadiee; Samia Touileb; Lubos Steskal
A Supervised Machine Learning Approach for Supporting Editorial Article Selection Working paper
2024.
BibTeX | Tags: | Links:
@workingpaper{supervisedmachin24,
title = {A Supervised Machine Learning Approach for Supporting Editorial Article Selection},
author = {Bilal Mahmood and Mehdi Elahi and Fahrhad Vadiee and Samia Touileb and Lubos Steskal},
url = {https://mediafutures.no/inra_long_paper_for_workshop_2024__ml_/},
year = {2024},
date = {2024-11-05},
issue = {INRA Long paper 2024},
keywords = {},
pubstate = {published},
tppubtype = {workingpaper}
}
Enrico Motta; Francesco Osborne; Martino M. L. Pulici; Angelo Antonio Salatino; Iman Naja
Capturing the Viewpoint Dynamics in the News Domain Best Paper Book Chapter
In: pp. 18-34, Springer Nature Switzerland, Knowledge Engineering and Knowledge Management, 2024.
Abstract | BibTeX | Tags: | Links:
@inbook{capt24,
title = {Capturing the Viewpoint Dynamics in the News Domain},
author = {Enrico Motta and Francesco Osborne and Martino M. L. Pulici and Angelo Antonio Salatino and Iman Naja},
url = {https://mediafutures.no/paper_20-2/},
year = {2024},
date = {2024-11-01},
pages = {18-34},
publisher = {Springer Nature Switzerland},
edition = {Knowledge Engineering and Knowledge Management},
abstract = {Despite the seismic changes brought about by the web and social media, mainstream news sources still play a crucial role in democratic societies. In particular, a healthy democracy requires a balanced and diverse media landscape, able to provide an arena in which the various topics and viewpoints relevant to the political discourse of the day are presented and discussed. To address this issue, we have developed a hybrid human-machine approach, which uses a Large Language Model first to help analysts identify the range of viewpoints relevant to the debate around a given topic and then to classify the claims expressed in the news corpus of interest with respect to the identified viewpoints. We tested a variety of LLMs on a benchmark corpus of news items drawn from British media sources. Our results indicate that GPT4o outperforms the other alternatives and can already provide effective support for this classification task, even when run in a zero-shot learning modality.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Despite the seismic changes brought about by the web and social media, mainstream news sources still play a crucial role in democratic societies. In particular, a healthy democracy requires a balanced and diverse media landscape, able to provide an arena in which the various topics and viewpoints relevant to the political discourse of the day are presented and discussed. To address this issue, we have developed a hybrid human-machine approach, which uses a Large Language Model first to help analysts identify the range of viewpoints relevant to the debate around a given topic and then to classify the claims expressed in the news corpus of interest with respect to the identified viewpoints. We tested a variety of LLMs on a benchmark corpus of news items drawn from British media sources. Our results indicate that GPT4o outperforms the other alternatives and can already provide effective support for this classification task, even when run in a zero-shot learning modality.
Jia Hua Jeng; Gloria Anne Babile Kasangu; Alain D. Starke; Erik Knudsen; Christoph Trattner
Negativity Sells? Using an LLM to Affectively Reframe News Articles in a Recommender System Workshop
2024.
Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links:
@workshop{negativ24,
title = {Negativity Sells? Using an LLM to Affectively Reframe News Articles in a Recommender System},
author = {Jia Hua Jeng and Gloria Anne Babile Kasangu and Alain D. Starke and Erik Knudsen and Christoph Trattner},
url = {https://mediafutures.no/inra_jeng/},
year = {2024},
date = {2024-10-30},
issue = {RecSys2024 - INRA workshop},
abstract = {Recent developments in artificial intelligence allow newsrooms to automate journalistic choices and processes. In doing so, news framing can impact people's engagement with news media, as well as their willingness to pay for news articles. Large Language Models (LLMs) can be used as a framing tool, aligning headlines with a news website user's preferences or state. It is, however, unknown how users perceive and experience the use of a platform with such LLM-reframed news headlines. We present the results of a user study (N = 300) with a news recommender system (NRS). Users had to read three news articles from The Washington Post from a preferred category (abortion, economics, gun control). Headlines were rewritten by an LLM (ChatGPT-4) and images were replaced in specific affective styles, across 2 (positive or negative headlines) x 3 (positive or negative image, or no image) between-subject framing conditions. We found that negatively framed images and text elicited negative emotions, while positive framing had little effect. Users were also more willing to pay for a news service when facing negatively framed headlines and images. Surprisingly, the congruency between text and image (i.e., both being framed negatively or positively) did not significantly impact engagement. We discuss how this study can shape further research on affective framing in news recommender systems and how such applications could impact journalism practices.},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {workshop}
}
Recent developments in artificial intelligence allow newsrooms to automate journalistic choices and processes. In doing so, news framing can impact people's engagement with news media, as well as their willingness to pay for news articles. Large Language Models (LLMs) can be used as a framing tool, aligning headlines with a news website user's preferences or state. It is, however, unknown how users perceive and experience the use of a platform with such LLM-reframed news headlines. We present the results of a user study (N = 300) with a news recommender system (NRS). Users had to read three news articles from The Washington Post from a preferred category (abortion, economics, gun control). Headlines were rewritten by an LLM (ChatGPT-4) and images were replaced in specific affective styles, across 2 (positive or negative headlines) x 3 (positive or negative image, or no image) between-subject framing conditions. We found that negatively framed images and text elicited negative emotions, while positive framing had little effect. Users were also more willing to pay for a news service when facing negatively framed headlines and images. Surprisingly, the congruency between text and image (i.e., both being framed negatively or positively) did not significantly impact engagement. We discuss how this study can shape further research on affective framing in news recommender systems and how such applications could impact journalism practices.
Jia Hua Jeng
Bridging Viewpoints in News with Recommender Systems Conference
ACM RecSys2024, 2024.
Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links:
@conference{bridging24,
title = {Bridging Viewpoints in News with Recommender Systems},
author = {Jia Hua Jeng},
url = {https://mediafutures.no/recsys24-phd/},
year = {2024},
date = {2024-10-08},
urldate = {2024-10-08},
booktitle = {ACM RecSys2024},
abstract = {News Recommender systems (NRSs) aid in decision-making in news media. However, undesired effects can emerge. Among these are selective exposures that may contribute to polarization, potentially reinforcing existing attitudes through belief perseverance—discounting contrary evidence due to their opposing attitudinal strength. This can be unsafe for people, making it difficult to accept information objectively. A crucial issue in news recommender system research is how to mitigate these undesired effects by designing recommender interfaces and machine learning models that enable people to consider to be more open to different perspectives. Alongside accurate models, the user experience is an equally important measure. Indeed, the core statistics are based on users’ behaviors and experiences in this research project. Therefore, this research agenda aims to steer the choices of readers' based on altering their attitudes. The core methods plan to concentrate on the interface design and ML model building involving manipulations of cues, users’ behaviors prediction, NRSs algorithm and changing the nudges. In sum, the project aims to provide insight in the extent to which news recommender systems can be effective in mitigating polarized opinions.},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {conference}
}
News Recommender systems (NRSs) aid in decision-making in news media. However, undesired effects can emerge. Among these are selective exposures that may contribute to polarization, potentially reinforcing existing attitudes through belief perseverance—discounting contrary evidence due to their opposing attitudinal strength. This can be unsafe for people, making it difficult to accept information objectively. A crucial issue in news recommender system research is how to mitigate these undesired effects by designing recommender interfaces and machine learning models that enable people to consider to be more open to different perspectives. Alongside accurate models, the user experience is an equally important measure. Indeed, the core statistics are based on users’ behaviors and experiences in this research project. Therefore, this research agenda aims to steer the choices of readers' based on altering their attitudes. The core methods plan to concentrate on the interface design and ML model building involving manipulations of cues, users’ behaviors prediction, NRSs algorithm and changing the nudges. In sum, the project aims to provide insight in the extent to which news recommender systems can be effective in mitigating polarized opinions.
Anastasiia Klimashevskaia; Mehdi Elahi; Dietmar Jannach; Christoph Trattner; Simen Buodd
Empowering Editors: How Automated Recommendations Support Editorial Article Curation Workshop
RecSys 2024, INRA workshop, 2024.
Abstract | BibTeX | Tags: | Links:
@workshop{empoweringANA24,
title = {Empowering Editors: How Automated Recommendations Support Editorial Article Curation},
author = {Anastasiia Klimashevskaia and Mehdi Elahi and Dietmar Jannach and Christoph Trattner and Simen Buodd},
url = {https://mediafutures.no/recsys2024-workshops_paper_119-3/},
year = {2024},
date = {2024-10-01},
urldate = {2024-10-01},
booktitle = {RecSys 2024, INRA workshop},
issue = {RecSys 2024, INRA workshop},
abstract = {The application of recommender systems in the news domain has experienced rapid growth in recent years. Various news outlets are proposing a full automation of a newspaper front page through automated recommendation. In this paper, however, we explore the synergy of editorial and algorithmic news curation by analyzing the front page of a real-world news platform, where news articles are either selected automatically by a recommendation algorithm or are selected manually by editors. An investigation of the interaction log data from an online newspaper revealed that while the editorial staff is focusing on content that is generally popular across large parts of the audience, the algorithmic curation can, in addition, provide small yet noteworthy personalization touches for individual readers. The results of the analysis demonstrate an example of a successful coexistence of editorial and algorithmic news curation.},
howpublished = {RecSys 2024, INRA workshop},
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
The application of recommender systems in the news domain has experienced rapid growth in recent years. Various news outlets are proposing a full automation of a newspaper front page through automated recommendation. In this paper, however, we explore the synergy of editorial and algorithmic news curation by analyzing the front page of a real-world news platform, where news articles are either selected automatically by a recommendation algorithm or are selected manually by editors. An investigation of the interaction log data from an online newspaper revealed that while the editorial staff is focusing on content that is generally popular across large parts of the audience, the algorithmic curation can, in addition, provide small yet noteworthy personalization touches for individual readers. The results of the analysis demonstrate an example of a successful coexistence of editorial and algorithmic news curation.
Fazle Rabbi
A Model-Based Framework for Exploring Conflict Dynamics Workshop
2024.
Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links:
@workshop{conflict24,
title = {A Model-Based Framework for Exploring Conflict Dynamics},
author = {Fazle Rabbi},
url = {https://mediafutures.no/3652620-3688206-2/},
year = {2024},
date = {2024-09-24},
issue = {ACM/IEEE },
abstract = {This paper introduces a novel framework for conflict analysis that leverages advanced visual modeling techniques. By employing comparative analysis, key variables influencing armed conflicts are identified and analyzed. The framework includes a meta-model representing domain concepts such as the goals and strategies of conflicting parties, escalating stages, and impacts of conflicts. Conflict escalation is a complex process characterized by interactions between opposing parties. This paper presents a structured model that outlines how conflicts evolve and intensify over time. We adapt a meta-modeling framework called the Diagram Predicate Framework (DPF) to represent conflict-related concepts and extend it to support abstract view generation. This framework facilitates the analysis of conflict trends and the study of dynamics across various levels of abstraction. A computational model based on category theory is proposed for trend analysis, enabling the extraction of patterns of conflict evolution and the comparison of strategies and goals at different escalation stages. Categorical operations such as pullback and limit construction are employed to compute conflict evolution and identify common structures among conflict instances, providing insights into conflict dynamics across diverse zones.},
keywords = {WP3: Media Content Production and Analysis},
pubstate = {published},
tppubtype = {workshop}
}
This paper introduces a novel framework for conflict analysis that leverages advanced visual modeling techniques. By employing comparative analysis, key variables influencing armed conflicts are identified and analyzed. The framework includes a meta-model representing domain concepts such as the goals and strategies of conflicting parties, escalating stages, and impacts of conflicts. Conflict escalation is a complex process characterized by interactions between opposing parties. This paper presents a structured model that outlines how conflicts evolve and intensify over time. We adapt a meta-modeling framework called the Diagram Predicate Framework (DPF) to represent conflict-related concepts and extend it to support abstract view generation. This framework facilitates the analysis of conflict trends and the study of dynamics across various levels of abstraction. A computational model based on category theory is proposed for trend analysis, enabling the extraction of patterns of conflict evolution and the comparison of strategies and goals at different escalation stages. Categorical operations such as pullback and limit construction are employed to compute conflict evolution and identify common structures among conflict instances, providing insights into conflict dynamics across diverse zones.
Ayoub El Majjodi; Sohail Ahmed Khan; Alain D. Starke; Mehdi Elahi; Christoph Trattner
Advancing Visual Food Attractiveness Predictions for Healthy Food Recommender Systems Conference
The ACM Conference on Recommender Systems (RecSys) 2024, 2024.
Abstract | BibTeX | Tags: | Links:
@conference{visualfood24,
title = {Advancing Visual Food Attractiveness Predictions for Healthy Food Recommender Systems},
author = {Ayoub El Majjodi and Sohail Ahmed Khan and Alain D. Starke and Mehdi Elahi and Christoph Trattner},
url = {https://mediafutures.no/healthrecsys-2024-ayoub-1/},
year = {2024},
date = {2024-09-17},
booktitle = {The ACM Conference on Recommender Systems (RecSys) 2024},
abstract = {The visual representation of food has a significant influence on
how people choose food in the real world but also in a digital food
recommender scenario. Previous studies on that matter show that
small change in visual features can change human decision-making,
regardless of whether the food is healthy or not. This paper reports
on a study that aims to understand further how users perceive
the attractiveness of food images in the digital world. In an online
mixed-methods survey (N=192), users provided visual attractive-
ness ratings on a 7-point scale and provided textual assessments
of the visual attractiveness of food images. We found a robust
correlation between fundamental visual features (e.g., contrast, col-
orfulness) and perceived image attractiveness. The analysis also
revealed that cooking skills predicted food image attractiveness
among user factors. Regarding food image dimensions, appearance
and perceived healthiness emerged to be significantly correlated
with user ratings for food image attractiveness.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
The visual representation of food has a significant influence on
how people choose food in the real world but also in a digital food
recommender scenario. Previous studies on that matter show that
small change in visual features can change human decision-making,
regardless of whether the food is healthy or not. This paper reports
on a study that aims to understand further how users perceive
the attractiveness of food images in the digital world. In an online
mixed-methods survey (N=192), users provided visual attractive-
ness ratings on a 7-point scale and provided textual assessments
of the visual attractiveness of food images. We found a robust
correlation between fundamental visual features (e.g., contrast, col-
orfulness) and perceived image attractiveness. The analysis also
revealed that cooking skills predicted food image attractiveness
among user factors. Regarding food image dimensions, appearance
and perceived healthiness emerged to be significantly correlated
with user ratings for food image attractiveness.
how people choose food in the real world but also in a digital food
recommender scenario. Previous studies on that matter show that
small change in visual features can change human decision-making,
regardless of whether the food is healthy or not. This paper reports
on a study that aims to understand further how users perceive
the attractiveness of food images in the digital world. In an online
mixed-methods survey (N=192), users provided visual attractive-
ness ratings on a 7-point scale and provided textual assessments
of the visual attractiveness of food images. We found a robust
correlation between fundamental visual features (e.g., contrast, col-
orfulness) and perceived image attractiveness. The analysis also
revealed that cooking skills predicted food image attractiveness
among user factors. Regarding food image dimensions, appearance
and perceived healthiness emerged to be significantly correlated
with user ratings for food image attractiveness.
Peter Røysland Aarnes; Vinay Setty; Petra Galuščáková
IAI Group at CheckThat! 2024: Transformer Models and Data Augmentation for Checkworthy Claim Detection Conference
Conference and Labs of the Evaluation Forum, 2024.
Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links:
@conference{checkthat24,
title = {IAI Group at CheckThat! 2024: Transformer Models and Data Augmentation for Checkworthy Claim Detection},
author = {Peter Røysland Aarnes and Vinay Setty and Petra Galuščáková},
url = {https://mediafutures.no/checkthat-lab-task-1-notebook/},
year = {2024},
date = {2024-09-13},
urldate = {2024-09-13},
booktitle = {Conference and Labs of the Evaluation Forum},
abstract = {This paper describes IAI group’s participation for automated check-worthiness estimation for claims, within
the framework of the 2024 CheckThat! Lab “Task 1: Check-Worthiness Estimation”. The task involves the
automated detection of check-worthy claims in English, Dutch, and Arabic political debates and Twitter data. We
utilized various pre-trained generative decoder and encoder transformer models, employing methods such as
few-shot chain-of-thought reasoning, fine-tuning, data augmentation, and transfer learning from one language
to another. Despite variable success in terms of performance, our models achieved notable placements on the
organizer’s leaderboard: ninth-best in English, third-best in Dutch, and the top placement in Arabic, utilizing
multilingual datasets for enhancing the generalizability of check-worthiness detection. Despite a significant drop
in performance on the unlabeled test dataset compared to the development test dataset, our findings contribute
to the ongoing efforts in claim detection research, highlighting the challenges and potential of language-specific
adaptations in claim verification systems.},
keywords = {WP3: Media Content Production and Analysis},
pubstate = {published},
tppubtype = {conference}
}
This paper describes IAI group’s participation for automated check-worthiness estimation for claims, within
the framework of the 2024 CheckThat! Lab “Task 1: Check-Worthiness Estimation”. The task involves the
automated detection of check-worthy claims in English, Dutch, and Arabic political debates and Twitter data. We
utilized various pre-trained generative decoder and encoder transformer models, employing methods such as
few-shot chain-of-thought reasoning, fine-tuning, data augmentation, and transfer learning from one language
to another. Despite variable success in terms of performance, our models achieved notable placements on the
organizer’s leaderboard: ninth-best in English, third-best in Dutch, and the top placement in Arabic, utilizing
multilingual datasets for enhancing the generalizability of check-worthiness detection. Despite a significant drop
in performance on the unlabeled test dataset compared to the development test dataset, our findings contribute
to the ongoing efforts in claim detection research, highlighting the challenges and potential of language-specific
adaptations in claim verification systems.
the framework of the 2024 CheckThat! Lab “Task 1: Check-Worthiness Estimation”. The task involves the
automated detection of check-worthy claims in English, Dutch, and Arabic political debates and Twitter data. We
utilized various pre-trained generative decoder and encoder transformer models, employing methods such as
few-shot chain-of-thought reasoning, fine-tuning, data augmentation, and transfer learning from one language
to another. Despite variable success in terms of performance, our models achieved notable placements on the
organizer’s leaderboard: ninth-best in English, third-best in Dutch, and the top placement in Arabic, utilizing
multilingual datasets for enhancing the generalizability of check-worthiness detection. Despite a significant drop
in performance on the unlabeled test dataset compared to the development test dataset, our findings contribute
to the ongoing efforts in claim detection research, highlighting the challenges and potential of language-specific
adaptations in claim verification systems.
Alain D. Starke; Vegard R. Solberg; Sebastian Øverhaug Larsen; Christoph Trattner
Examining the Merits of Feature-specific Similarity Functions in the News Domain using Human Judgments Journal Article
In: User Modeling and User-Adapted Interaction, 2024.
Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links:
@article{NewsDomainusing24,
title = {Examining the Merits of Feature-specific Similarity Functions in the News Domain using Human Judgments},
author = {Alain D. Starke and Vegard R. Solberg and Sebastian Øverhaug Larsen and Christoph Trattner},
url = {https://mediafutures.no/umuai_special_issue_news_similarity-1/},
year = {2024},
date = {2024-07-27},
urldate = {2024-07-27},
journal = {User Modeling and User-Adapted Interaction},
abstract = {Online news article recommendations are typically of the ‘more like this’ type, generated by similarity functions. Across three studies, we examined the representativeness of different similarity functions for news item retrieval, by comparing them to human judgments of similarity. In Study 1 (N = 401), participants assessed the overall similarity of ten randomly paired news articles on politics, and compared their judgments to different feature-specific similarity functions (e.g., based on body text or images). In Study 2, we checked for domain differences in a mixed-methods survey (N = 45), surfacing evidence that the effectiveness of similarity functions differs across different news categories (‘Recent Events’, ‘Sport’). In Study 3 (N = 173), we improved the design of Study 1, by controlling for how news articles were matched, differentiating between dissimilar news articles and articles that were matched on a shared topic, named entities, and/or date of publication, across ‘Recent Events’ and ‘Sport’ categories.
Across all studies, we found that users mostly used text-based features (e.g., body text, title) for their similarity judgments, while BodyText:TF-IDF was found to be the most representative for their judgments. Moreover, the strength of similarity judgments by humans and similarity scores by feature-specific functions was strongly affected
by how news article pairs were matched. We show that humans and similarity functions are better aligned when two news articles are more alike, such as in a news recommendation scenario.},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {article}
}
Online news article recommendations are typically of the ‘more like this’ type, generated by similarity functions. Across three studies, we examined the representativeness of different similarity functions for news item retrieval, by comparing them to human judgments of similarity. In Study 1 (N = 401), participants assessed the overall similarity of ten randomly paired news articles on politics, and compared their judgments to different feature-specific similarity functions (e.g., based on body text or images). In Study 2, we checked for domain differences in a mixed-methods survey (N = 45), surfacing evidence that the effectiveness of similarity functions differs across different news categories (‘Recent Events’, ‘Sport’). In Study 3 (N = 173), we improved the design of Study 1, by controlling for how news articles were matched, differentiating between dissimilar news articles and articles that were matched on a shared topic, named entities, and/or date of publication, across ‘Recent Events’ and ‘Sport’ categories.
Across all studies, we found that users mostly used text-based features (e.g., body text, title) for their similarity judgments, while BodyText:TF-IDF was found to be the most representative for their judgments. Moreover, the strength of similarity judgments by humans and similarity scores by feature-specific functions was strongly affected
by how news article pairs were matched. We show that humans and similarity functions are better aligned when two news articles are more alike, such as in a news recommendation scenario.
Across all studies, we found that users mostly used text-based features (e.g., body text, title) for their similarity judgments, while BodyText:TF-IDF was found to be the most representative for their judgments. Moreover, the strength of similarity judgments by humans and similarity scores by feature-specific functions was strongly affected
by how news article pairs were matched. We show that humans and similarity functions are better aligned when two news articles are more alike, such as in a news recommendation scenario.
Bilal Mahmood; Mehdi Elahi; Samia Touileb; Lubos Steskal; Christoph Trattner
Incorporating Editorial Feedback in the Evaluation of News Recommender Systems Conference
ACM UMAP 2024, 2024.
Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links:
@conference{incoed24,
title = {Incorporating Editorial Feedback in the Evaluation of News Recommender Systems},
author = {Bilal Mahmood and Mehdi Elahi and Samia Touileb and Lubos Steskal and Christoph Trattner},
url = {https://mediafutures.no/lbr_umap_editorial_component_in_nrs/},
year = {2024},
date = {2024-07-01},
urldate = {2024-07-01},
booktitle = {ACM UMAP 2024},
abstract = {Research in the recommender systems field typically applies a rather traditional evaluation methodology when assessing the quality of recommendations. This methodology heavily relies on incorporating different forms of user feedback (e.g., clicks) representing the specific needs and interests of the users. While this methodology may offer various benefits, it may fail to comprehensively project the complexities of certain application domains, such as the news domain. This domain is distinct from other domains primarily due to the strong influence of editorial control in the news delivery process. Incorporation of this role can profoundly impact how the relevance of news articles is measured when recommended to the users. Despite its critical importance, there appears to be a research gap in investigating the dynamics between the roles of editorial control and personalization in the community of recommender systems. In this paper, we address this gap by conducting experiments where the relevance of recommendations is assessed from an editorial perspective. We received a real-world dataset from TV 2, one of the largest editor-managed commercial media houses in Norway, which includes editors’ feedback on how news articles are being related. In our experiment, we considered a scenario where algorithm-generated recommendations, using the K-Nearest Neighbor (KNN) model, employing various text embedding models to encode different sections of the news articles (e.g., title, lead title, body text, and full text), are compared against the editorial feedback. The results are promising, demonstrating the effectiveness of the recommendation in fulfilling the editorial prospects.},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {conference}
}
Research in the recommender systems field typically applies a rather traditional evaluation methodology when assessing the quality of recommendations. This methodology heavily relies on incorporating different forms of user feedback (e.g., clicks) representing the specific needs and interests of the users. While this methodology may offer various benefits, it may fail to comprehensively project the complexities of certain application domains, such as the news domain. This domain is distinct from other domains primarily due to the strong influence of editorial control in the news delivery process. Incorporation of this role can profoundly impact how the relevance of news articles is measured when recommended to the users. Despite its critical importance, there appears to be a research gap in investigating the dynamics between the roles of editorial control and personalization in the community of recommender systems. In this paper, we address this gap by conducting experiments where the relevance of recommendations is assessed from an editorial perspective. We received a real-world dataset from TV 2, one of the largest editor-managed commercial media houses in Norway, which includes editors’ feedback on how news articles are being related. In our experiment, we considered a scenario where algorithm-generated recommendations, using the K-Nearest Neighbor (KNN) model, employing various text embedding models to encode different sections of the news articles (e.g., title, lead title, body text, and full text), are compared against the editorial feedback. The results are promising, demonstrating the effectiveness of the recommendation in fulfilling the editorial prospects.
Alain D. Starke; Anders Sandvik Bremnes; Erik Knudsen; Damian Trilling; Christoph Trattner
Perception versus Reality: Evaluating User Awareness of Political Selective Exposure in News Recommender Systems Conference
ACM UMAP 2024, 2024.
Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links:
@conference{percepvsreal24,
title = {Perception versus Reality: Evaluating User Awareness of Political Selective Exposure in News Recommender Systems},
author = {Alain D. Starke and Anders Sandvik Bremnes and Erik Knudsen and Damian Trilling and Christoph Trattner},
url = {https://mediafutures.no/umap2024___erik_alain_damian_anders_christoph/},
year = {2024},
date = {2024-07-01},
urldate = {2024-07-01},
booktitle = {ACM UMAP 2024},
abstract = {News Recommender Systems (NRSs) have become increasingly pivotal in shaping the news landscape, particularly in how news is disseminated. This has also led to concerns about information diversity, especially regarding selective exposure in the realm of political news. Users may not recognize that news content presented to them is subject to selective exposure, through users that incorporate political beliefs. Within the U.S. two-party system, our research explores the interactions between NRSs and users’ ability to discern news articles that align with their political biases. We performed an online experiment (N = 160) to address the issue of user awareness and self-recognition of selective exposure within NRSs. Users were asked to select any number of news articles that matched their political orientation (i.e., Democrat or Republican) from a list of 50 news articles (5 Democrat, 5 Republican, 40 filler articles), which were either ranked saliently towards their political orientation or randomly. Contrary to expectations, our findings reveal no significant difference in article selection between participants exposed to a baseline random order and those who where presented with the more salient and easy to select version. We did observe that Republicans performed worse than Democrats in identifying aligning articles, based on precision and recall metrics.},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {conference}
}
News Recommender Systems (NRSs) have become increasingly pivotal in shaping the news landscape, particularly in how news is disseminated. This has also led to concerns about information diversity, especially regarding selective exposure in the realm of political news. Users may not recognize that news content presented to them is subject to selective exposure, through users that incorporate political beliefs. Within the U.S. two-party system, our research explores the interactions between NRSs and users’ ability to discern news articles that align with their political biases. We performed an online experiment (N = 160) to address the issue of user awareness and self-recognition of selective exposure within NRSs. Users were asked to select any number of news articles that matched their political orientation (i.e., Democrat or Republican) from a list of 50 news articles (5 Democrat, 5 Republican, 40 filler articles), which were either ranked saliently towards their political orientation or randomly. Contrary to expectations, our findings reveal no significant difference in article selection between participants exposed to a baseline random order and those who where presented with the more salient and easy to select version. We did observe that Republicans performed worse than Democrats in identifying aligning articles, based on precision and recall metrics.
Jia Hua Jeng; Gloria Anne Babile Kasangu; Alain D. Starke; Christoph Trattner
Emotional Reframing of Economic News using a Large Language Model Conference
ACM UMAP 2024, 2024.
Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links:
@conference{emorefram24,
title = {Emotional Reframing of Economic News using a Large Language Model},
author = {Jia Hua Jeng and Gloria Anne Babile Kasangu and Alain D. Starke and Christoph Trattner},
url = {https://mediafutures.no/umap2024___jeng_alain_gloria_christoph__workshop_-3/},
year = {2024},
date = {2024-07-01},
urldate = {2024-07-01},
booktitle = {ACM UMAP 2024},
abstract = {News media framing can shape public perception and potentially polarize views. Emotional language can exacerbate these framing effects, as a user’s emotional state can be an important contextual factor to use in news recommendation. Our research explores the relation between emotional framing techniques and the emotional states of readers, as well as readers’ perceived trust in specific news articles. Users (N = 200) had to read three economic news articles from the Washington Post. We used ChatGPT-4 to reframe news articles with specific emotional languages (Anger, Fear, Hope), compared to a neutral baseline reframed by a human journalist. Our results revealed that negative framing (Anger, Fear) elicited stronger negative emotional states among users than the neutral baseline, while Hope led to little changes overall. In contrast, perceived trust levels varied little across the different conditions. We discuss the implications of our findings and how emotional framing could affect societal polarization issues},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {conference}
}
News media framing can shape public perception and potentially polarize views. Emotional language can exacerbate these framing effects, as a user’s emotional state can be an important contextual factor to use in news recommendation. Our research explores the relation between emotional framing techniques and the emotional states of readers, as well as readers’ perceived trust in specific news articles. Users (N = 200) had to read three economic news articles from the Washington Post. We used ChatGPT-4 to reframe news articles with specific emotional languages (Anger, Fear, Hope), compared to a neutral baseline reframed by a human journalist. Our results revealed that negative framing (Anger, Fear) elicited stronger negative emotional states among users than the neutral baseline, while Hope led to little changes overall. In contrast, perceived trust levels varied little across the different conditions. We discuss the implications of our findings and how emotional framing could affect societal polarization issues
Daniel Rosnes; Alain Starke; Christoph Trattner
Shaping the Future of Content-based News Recommenders: Insights from Evaluating Feature-Specific Similarity Metrics Conference
ACM UMAP '24, 2024.
Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links:
@conference{umap2024Daniel,
title = {Shaping the Future of Content-based News Recommenders: Insights from Evaluating Feature-Specific Similarity Metrics},
author = {Daniel Rosnes and Alain Starke and Christoph Trattner },
url = {https://mediafutures.no/umap2024/},
year = {2024},
date = {2024-07-01},
booktitle = {ACM UMAP '24},
abstract = {In news media, recommender system technology faces several domain-specific challenges. The continuous stream of new content and users deems content-based recommendation strategies, based on similar-item retrieval, to remain popular. However, a persistent challenge is to select relevant features and corresponding similarity functions, and whether this depends on the specific context. We evaluated feature-specific similarity metrics using human similarity judgments across national and local news domains. We performed an online experiment ($N = 141$) where we asked participants to judge the similarity between pairs of randomly sampled news articles. We had three contributions: (1) comparing novel metrics based on large language models to ones traditionally used in news recommendations, (2) exploring differences in similarity judgments across national and local news domains, and (3) examining which content-based strategies were perceived as appropriate in the news domain. Our results showed that one of the novel large language model based metrics (SBERT) was highly correlated with human judgments, while there were only small, most non-significant differences across national and local news domains. Finally, we found that while it may be possible to automatically recommend similar news using feature-specific metrics, their representativeness and appropriateness varied. We explain how our findings can guide the design of future content-based and hybrid recommender strategies in the news domain.},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {conference}
}
In news media, recommender system technology faces several domain-specific challenges. The continuous stream of new content and users deems content-based recommendation strategies, based on similar-item retrieval, to remain popular. However, a persistent challenge is to select relevant features and corresponding similarity functions, and whether this depends on the specific context. We evaluated feature-specific similarity metrics using human similarity judgments across national and local news domains. We performed an online experiment ($N = 141$) where we asked participants to judge the similarity between pairs of randomly sampled news articles. We had three contributions: (1) comparing novel metrics based on large language models to ones traditionally used in news recommendations, (2) exploring differences in similarity judgments across national and local news domains, and (3) examining which content-based strategies were perceived as appropriate in the news domain. Our results showed that one of the novel large language model based metrics (SBERT) was highly correlated with human judgments, while there were only small, most non-significant differences across national and local news domains. Finally, we found that while it may be possible to automatically recommend similar news using feature-specific metrics, their representativeness and appropriateness varied. We explain how our findings can guide the design of future content-based and hybrid recommender strategies in the news domain.
Anastasiia Klimashevskaia; Dietmar Jannach; Mehdi Elahi; Christoph Trattner
A Survey on Popularity Bias in Recommender Systems Journal Article
In: User Modeling and User-Adapted Interaction (UMUAI), 2024.
Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links:
@article{biasanas24,
title = {A Survey on Popularity Bias in Recommender Systems},
author = {Anastasiia Klimashevskaia and Dietmar Jannach and Mehdi Elahi and Christoph Trattner},
url = {https://mediafutures.no/popularitybias_literature_review-5/},
year = {2024},
date = {2024-06-13},
urldate = {2024-06-13},
journal = {User Modeling and User-Adapted Interaction (UMUAI)},
abstract = {Recommender systems help people find relevant content in a personalized way. One main promise of such systems is that they are able to increase the visibility of items in the long tail, i.e., the lesser-
known items in a catalogue. Existing research, however, suggests that in many situations today’s recommendation algorithms instead exhibit a popularity bias, meaning that they often focus on rather popular items in their recommendations. Such a bias may not only lead to the limited value of the recommendations for consumers and providers in the short run, but it may also cause undesired reinforcement effects over time. In this paper, we discuss the potential reasons for popularity bias and review existing approaches to detect, quantify and mitigate popularity bias in
recommender systems. Our survey, therefore, includes both an overview
of the computational metrics used in the literature as well as a review of the main technical approaches to reduce the bias. Furthermore, we critically discuss today’s literature, where we observe that the research is almost entirely based on computational experiments and on certain
assumptions regarding the practical effects of including long-tail items in the recommendations.},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {article}
}
Recommender systems help people find relevant content in a personalized way. One main promise of such systems is that they are able to increase the visibility of items in the long tail, i.e., the lesser-
known items in a catalogue. Existing research, however, suggests that in many situations today’s recommendation algorithms instead exhibit a popularity bias, meaning that they often focus on rather popular items in their recommendations. Such a bias may not only lead to the limited value of the recommendations for consumers and providers in the short run, but it may also cause undesired reinforcement effects over time. In this paper, we discuss the potential reasons for popularity bias and review existing approaches to detect, quantify and mitigate popularity bias in
recommender systems. Our survey, therefore, includes both an overview
of the computational metrics used in the literature as well as a review of the main technical approaches to reduce the bias. Furthermore, we critically discuss today’s literature, where we observe that the research is almost entirely based on computational experiments and on certain
assumptions regarding the practical effects of including long-tail items in the recommendations.
known items in a catalogue. Existing research, however, suggests that in many situations today’s recommendation algorithms instead exhibit a popularity bias, meaning that they often focus on rather popular items in their recommendations. Such a bias may not only lead to the limited value of the recommendations for consumers and providers in the short run, but it may also cause undesired reinforcement effects over time. In this paper, we discuss the potential reasons for popularity bias and review existing approaches to detect, quantify and mitigate popularity bias in
recommender systems. Our survey, therefore, includes both an overview
of the computational metrics used in the literature as well as a review of the main technical approaches to reduce the bias. Furthermore, we critically discuss today’s literature, where we observe that the research is almost entirely based on computational experiments and on certain
assumptions regarding the practical effects of including long-tail items in the recommendations.
Peter Andrews; Oda Elise Nordberg; Frode Guribye; Morten Fjeld; Njål Borch
Designing for Automated Sports Commentary Systems Conference
IMX'24, 2024.
Abstract | BibTeX | Tags: WP4: Media Content Interaction and Accessibility | Links:
@conference{designing_for_automated24,
title = {Designing for Automated Sports Commentary Systems},
author = {Peter Andrews and Oda Elise Nordberg and Frode Guribye and Morten Fjeld and Njål Borch },
url = {https://mediafutures.no/designing_for_automated_sports_commentary_systems-2/},
year = {2024},
date = {2024-06-12},
booktitle = {IMX'24},
abstract = {Advancements in Natural Language Processing (NLP) and Computer Vision (CV) are revolutionizing how we experience sports broadcasting. Traditionally, sports commentary has played a crucial role in enhancing viewer understanding and engagement with live games. Yet, the prospects of automated commentary, especially in light of these technological advancements and their impact on viewers’ experience, remain largely unexplored. This paper elaborates upon an innovative automated commentary system that integrates NLP and CV to provide a multimodal experience, combining auditory feedback through text-to-speech and visual cues, known as italicizing, for real-time in-game commentary. The system supports color commentary, which aims to inform the viewer of information surrounding the game by pulling additional content from a database. Moreover, it also supports play-by-play commentary covering in-game developments derived from an event system based on CV. As the system reinvents the role of commentary in sports video, we must consider the design and implications of multimodal artificial commentators. A focused user study with eight participants aimed at understanding the design implications of such multimodal artificial commentators reveals critical insights. Key findings emphasize the importance of language precision, content relevance, and delivery style in automated commentary, underscoring the necessity for personalization to meet diverse viewer preferences. Our results validate the potential value and effectiveness of multimodal feedback and derive design considerations, particularly in personalizing content to revolutionize the role of commentary in sports broadcasts.},
keywords = {WP4: Media Content Interaction and Accessibility},
pubstate = {published},
tppubtype = {conference}
}
Advancements in Natural Language Processing (NLP) and Computer Vision (CV) are revolutionizing how we experience sports broadcasting. Traditionally, sports commentary has played a crucial role in enhancing viewer understanding and engagement with live games. Yet, the prospects of automated commentary, especially in light of these technological advancements and their impact on viewers’ experience, remain largely unexplored. This paper elaborates upon an innovative automated commentary system that integrates NLP and CV to provide a multimodal experience, combining auditory feedback through text-to-speech and visual cues, known as italicizing, for real-time in-game commentary. The system supports color commentary, which aims to inform the viewer of information surrounding the game by pulling additional content from a database. Moreover, it also supports play-by-play commentary covering in-game developments derived from an event system based on CV. As the system reinvents the role of commentary in sports video, we must consider the design and implications of multimodal artificial commentators. A focused user study with eight participants aimed at understanding the design implications of such multimodal artificial commentators reveals critical insights. Key findings emphasize the importance of language precision, content relevance, and delivery style in automated commentary, underscoring the necessity for personalization to meet diverse viewer preferences. Our results validate the potential value and effectiveness of multimodal feedback and derive design considerations, particularly in personalizing content to revolutionize the role of commentary in sports broadcasts.
Aida Ashrafi; Bjørnar Tessem; Katja Enberg
Analysing Unlabeled Data with Randomness and Noise: The Case of Fishery Catch Reports Conference
14th Scandinavian Conference on Artificial Intelligence SCAI 2024, 2024.
Abstract | BibTeX | Tags: | Links:
@conference{fisherycatch24,
title = {Analysing Unlabeled Data with Randomness and Noise: The Case of Fishery Catch Reports},
author = {Aida Ashrafi and Bjørnar Tessem and Katja Enberg},
url = {https://mediafutures.no/analysing_unlabeled_data_with_randomness_and_noise/},
year = {2024},
date = {2024-06-10},
booktitle = {14th Scandinavian Conference on Artificial Intelligence SCAI 2024},
abstract = {Detecting violations within fishing activity reports is crucial for ensuring the sustainable utilization of fish resources, and employing machine learning methods holds promise for uncovering hidden patterns within this complex dataset. Given that these violations are infrequent occurrences, as fishermen generally adhere to regulations, identifying them becomes akin to an anomaly outlier detection task. Since labeled data distinguishing between normal and anomalous instances is not available for catch reports from Norwegian waters, we have opted for more conventional approaches, such as clustering methods, to identify potential clusters and outliers. Moreover, the catch reports inherently exhibit randomness and noise due to environmental factors and potential errors made by fishermen during report registration which complicates the processes of scaling, clustering, and anomaly detection. Through experimentation with various scaling and clustering techniques, we have observed that many of these methods tend to group the data based on the species caught, exhibiting a high level of agreement in cluster formation, indicating the stability of the clusters. Anomaly detection methods, however, yield varying potential outliers as it is a more challenging task.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Detecting violations within fishing activity reports is crucial for ensuring the sustainable utilization of fish resources, and employing machine learning methods holds promise for uncovering hidden patterns within this complex dataset. Given that these violations are infrequent occurrences, as fishermen generally adhere to regulations, identifying them becomes akin to an anomaly outlier detection task. Since labeled data distinguishing between normal and anomalous instances is not available for catch reports from Norwegian waters, we have opted for more conventional approaches, such as clustering methods, to identify potential clusters and outliers. Moreover, the catch reports inherently exhibit randomness and noise due to environmental factors and potential errors made by fishermen during report registration which complicates the processes of scaling, clustering, and anomaly detection. Through experimentation with various scaling and clustering techniques, we have observed that many of these methods tend to group the data based on the species caught, exhibiting a high level of agreement in cluster formation, indicating the stability of the clusters. Anomaly detection methods, however, yield varying potential outliers as it is a more challenging task.
Duc-Tien Dang-Nguyen; Sohail Ahmed Khan; Michael Riegler; Pål Halvorsen; Anh-Duy Tran; Minh-Son Dao; Minh-Triet Tran
Overview of the Grand Challenge on Detecting Cheapfakes Proceedings Article
In: Proceedings of the 2024 International Conference on Multimedia Retrieval (ICMR’24), 2024.
Abstract | BibTeX | Tags: Fake Detection | Links:
@inproceedings{deteccheapfakes,
title = {Overview of the Grand Challenge on Detecting Cheapfakes},
author = {Duc-Tien Dang-Nguyen and Sohail Ahmed Khan and Michael Riegler and Pål Halvorsen and Anh-Duy Tran and Minh-Son Dao and Minh-Triet Tran},
url = {https://mediafutures.no/grand_challenge_on_detecting_cheapfakes-2/},
year = {2024},
date = {2024-06-10},
urldate = {2024-06-10},
booktitle = {Proceedings of the 2024 International Conference on Multimedia Retrieval (ICMR’24)},
abstract = {Cheapfake is a recently coined term that encompasses non-AI ("cheap") manipulations of multimedia content. Cheapfakes are known to be more prevalent than deepfakes. Cheapfake media can be created using editing software for image/video manipulations, or even without using any software, by simply altering the context of an image/video by sharing the media alongside misleading claims. This alteration of context is referred to as out-of-context (OOC) misuse of media. OOC media is much harder to detect than fake media, since the images and videos are not tampered. In this challenge, we focus on detecting OOC images, and more specifically the misuse of real photographs with conflicting image captions in news items. The aim of this challenge is to develop and benchmark models that can be used to detect whether given samples (news image and associated captions) are OOC, based on the recently compiled COSMOS dataset.},
keywords = {Fake Detection},
pubstate = {published},
tppubtype = {inproceedings}
}
Cheapfake is a recently coined term that encompasses non-AI ("cheap") manipulations of multimedia content. Cheapfakes are known to be more prevalent than deepfakes. Cheapfake media can be created using editing software for image/video manipulations, or even without using any software, by simply altering the context of an image/video by sharing the media alongside misleading claims. This alteration of context is referred to as out-of-context (OOC) misuse of media. OOC media is much harder to detect than fake media, since the images and videos are not tampered. In this challenge, we focus on detecting OOC images, and more specifically the misuse of real photographs with conflicting image captions in news items. The aim of this challenge is to develop and benchmark models that can be used to detect whether given samples (news image and associated captions) are OOC, based on the recently compiled COSMOS dataset.
Samia Touileb; Jeanett Murstad; Petter Mæhlum; Lubos Steskal; Lilja Charlotte Storset; Huiling You; Lilja Øvrelid
EDEN: A Dataset for Event Detection in Norwegian News Conference
LREC-COLING 2024, 2024.
Abstract | BibTeX | Tags: WP5: Norwegian Language Technologies | Links:
@conference{EDEN,
title = {EDEN: A Dataset for Event Detection in Norwegian News},
author = {Samia Touileb and Jeanett Murstad and Petter Mæhlum and Lubos Steskal and Lilja Charlotte Storset and Huiling You and Lilja Øvrelid},
url = {https://mediafutures.no/2024-lrec-main-488/},
year = {2024},
date = {2024-05-23},
booktitle = {LREC-COLING 2024},
abstract = {We present EDEN, the first Norwegian dataset annotated with event information at the sentence level, adapting the
widely used ACE event schema to Norwegian. The paper describes the manual annotation of Norwegian text as well
as transcribed speech in the news domain, together with inter-annotator agreement and discussions of relevant
dataset statistics. We also present preliminary modeling results using a graph-based event parser. The resulting
dataset will be made freely available for download and use.
},
keywords = {WP5: Norwegian Language Technologies},
pubstate = {published},
tppubtype = {conference}
}
We present EDEN, the first Norwegian dataset annotated with event information at the sentence level, adapting the
widely used ACE event schema to Norwegian. The paper describes the manual annotation of Norwegian text as well
as transcribed speech in the news domain, together with inter-annotator agreement and discussions of relevant
dataset statistics. We also present preliminary modeling results using a graph-based event parser. The resulting
dataset will be made freely available for download and use.
widely used ACE event schema to Norwegian. The paper describes the manual annotation of Norwegian text as well
as transcribed speech in the news domain, together with inter-annotator agreement and discussions of relevant
dataset statistics. We also present preliminary modeling results using a graph-based event parser. The resulting
dataset will be made freely available for download and use.
Andreas L. Opdahl; Natali Helberger; Nicholas Diakopoulos
Guest Editorial: AI and the news Journal Article
In: AI Magazine, 2024.
BibTeX | Tags: | Links:
@article{aiandnewa,
title = {Guest Editorial: AI and the news},
author = {Andreas L. Opdahl and Natali Helberger and Nicholas Diakopoulos},
url = {https://mediafutures.no/guest_editorial_ai_and_the_news-2/},
year = {2024},
date = {2024-05-15},
journal = {AI Magazine},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Jo Dugstad Wake; Frode
Avoiding "metal astray": experience evaluation of virtual reality training for melting furnace operators Proceedings Article
In: Proceedings of the 21st ISCRAM Conference, 2024.
Abstract | BibTeX | Tags: | Links:
@inproceedings{metalstray24,
title = {Avoiding "metal astray": experience evaluation of virtual reality training for melting furnace operators},
author = {Jo Dugstad Wake and Frode},
url = {https://mediafutures.no/vr_iscram_print_2024/},
year = {2024},
date = {2024-05-01},
booktitle = {Proceedings of the 21st ISCRAM Conference},
abstract = {The work of melting furnace operators is potentially hazardous and serious accidents do occur. Training on the monitoring and safe operation of furnaces is key to the safety of the operators and their surroundings. Virtual Reality (VR) environments can simulate safety critical work environments and provide realistic, safe and engaging ways to train on situations otherwise unavailable. To address the potential of using VR in safety training, the VR environment called VR Safe was developed. This paper presents a study of the user experience of training safety critical procedures in VR. VR Safe simulates malfunction in one of the most important systems regarding safe operation of furnaces: furnace cooling system monitoring and how to respond to cooling system failure. The evaluation included professional furnace operators, and was focused on usability of the system, user engagement and the training value as it relates to the operators' work.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The work of melting furnace operators is potentially hazardous and serious accidents do occur. Training on the monitoring and safe operation of furnaces is key to the safety of the operators and their surroundings. Virtual Reality (VR) environments can simulate safety critical work environments and provide realistic, safe and engaging ways to train on situations otherwise unavailable. To address the potential of using VR in safety training, the VR environment called VR Safe was developed. This paper presents a study of the user experience of training safety critical procedures in VR. VR Safe simulates malfunction in one of the most important systems regarding safe operation of furnaces: furnace cooling system monitoring and how to respond to cooling system failure. The evaluation included professional furnace operators, and was focused on usability of the system, user engagement and the training value as it relates to the operators' work.
Maria Soledad Pera; Federica Cena; Monica Landoni; Cataldo Musto; Alain D. Starke
Human Factors in User Modeling for Intelligent Systems Book Chapter
In: pp. 3–42, A Human-Centered Perspective of Intelligent Personalized Environments and Systems, 2024.
Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links:
@inbook{Alain_humanF24,
title = {Human Factors in User Modeling for Intelligent Systems},
author = {Maria Soledad Pera and Federica Cena and Monica Landoni and Cataldo Musto and Alain D. Starke},
url = {https://mediafutures.no/pera2024-book-chapter-holistic-user-modeling/},
year = {2024},
date = {2024-05-01},
urldate = {2024-05-01},
pages = {3–42},
edition = {A Human-Centered Perspective of Intelligent Personalized Environments and Systems},
series = {Human–Computer Interaction Series.},
abstract = {In the current digital landscape, humans take center stage. This has caused a paradigm shift in the realm of intelligent technologies, prompting researchers and (industry) practitioners to reflect on the challenges and complexities involved in understanding the (potential) users of the technologies they develop. In this chapter, we provide an overview of human factors in user modeling, a core component of human-centered intelligent solutions. We discuss critical concepts, dimensions, and theories that inform the design of user models that are more attuned to human characteristics. Additionally, we emphasize the need for a comprehensive user model that simultaneously considers multiple factors to represent the intricacies of individuals’ interests and behaviors. Such a holistic model can, in turn, shape the design of intelligent solutions that are better able to adapt and cater to a wide range of user groups.},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {inbook}
}
In the current digital landscape, humans take center stage. This has caused a paradigm shift in the realm of intelligent technologies, prompting researchers and (industry) practitioners to reflect on the challenges and complexities involved in understanding the (potential) users of the technologies they develop. In this chapter, we provide an overview of human factors in user modeling, a core component of human-centered intelligent solutions. We discuss critical concepts, dimensions, and theories that inform the design of user models that are more attuned to human characteristics. Additionally, we emphasize the need for a comprehensive user model that simultaneously considers multiple factors to represent the intricacies of individuals’ interests and behaviors. Such a holistic model can, in turn, shape the design of intelligent solutions that are better able to adapt and cater to a wide range of user groups.
Alain D. Starke; Martijn C. Willemsen
Psychologically Informed Design of Energy Recommender Systems: Are Nudges Still Effective in Tailored Choice Environments? Book Chapter
In: pp. 221–259, A Human-Centered Perspective of Intelligent Personalized Environments and Systems, 2024.
BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links:
@inbook{Alain_pysch24,
title = {Psychologically Informed Design of Energy Recommender Systems: Are Nudges Still Effective in Tailored Choice Environments?},
author = {Alain D. Starke and Martijn C. Willemsen},
url = {https://mediafutures.no/starke2024-book-chapter-psych-informed-energy-recsys-4/},
year = {2024},
date = {2024-05-01},
urldate = {2024-05-01},
pages = {221–259},
edition = {A Human-Centered Perspective of Intelligent Personalized Environments and Systems},
series = {Human–Computer Interaction Series},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {inbook}
}
Peter Andrews; Njål Borch; Morten Fjeld
FootyVision: Multi-Object Tracking, Localisation, and Augmentation of Players and Ball in Football Video Conference
ACM ICMIP, 2024.
Abstract | BibTeX | Tags: WP4: Media Content Interaction and Accessibility | Links:
@conference{Footyvision1,
title = {FootyVision: Multi-Object Tracking, Localisation, and Augmentation of Players and Ball in Football Video},
author = {Peter Andrews and Njål Borch and Morten Fjeld},
url = {https://mediafutures.no/peterandrews-footyvision-icmip24-final/},
year = {2024},
date = {2024-04-20},
booktitle = {ACM ICMIP},
abstract = {Football video content analysis is a rapidly evolving field aiming to enrich the viewing experience of football matches. Current research often focuses on specific tasks like player and/or ball detection, tracking, and localisation in top-down views. Our study strives to integrate these efforts into a comprehensive Multi-Object Tracking (MOT) model capable of handling perspective transformations. Our framework, FootyVision, employs a YOLOv7 backbone trained on an extended player and ball dataset. The MOT module builds a gallery and assigns identities via the Hungarian algorithm based on feature embeddings, bounding box intersection over union, distance, and velocity. A novel component of our model is the perspective transformation module that leverages activation maps from the YOLOv7 backbone to compute homographies using lines, intersection points, and ellipses. This method effectively adapts to dynamic and uncalibrated video data, even in viewpoints with limited visual information. In terms of performance, FootyVision sets new benchmarks. The model achieves a mean average precision (mAP) of 95.7% and an F1-score of 95.5% in object detection. For MOT, it demonstrates robust capabilities, with an IDF1 score of approximately 93% on both ISSIA and SoccerNet datasets. For SoccerNet, it reaches a MOTA of 94.04% and shows competitive results for ISSIA. Additionally, FootyVision scores a HOTA(0) of 93.1% and an overall HOTA of 72.16% for the SoccerNet dataset. Our ablation study confirms the effectiveness of the selected tracking features and identifies key attributes for further improvement. While the model excels in maintaining track accuracy throughout the testing dataset, we recognise the potential to enhance spatial-location accuracy.},
keywords = {WP4: Media Content Interaction and Accessibility},
pubstate = {published},
tppubtype = {conference}
}
Football video content analysis is a rapidly evolving field aiming to enrich the viewing experience of football matches. Current research often focuses on specific tasks like player and/or ball detection, tracking, and localisation in top-down views. Our study strives to integrate these efforts into a comprehensive Multi-Object Tracking (MOT) model capable of handling perspective transformations. Our framework, FootyVision, employs a YOLOv7 backbone trained on an extended player and ball dataset. The MOT module builds a gallery and assigns identities via the Hungarian algorithm based on feature embeddings, bounding box intersection over union, distance, and velocity. A novel component of our model is the perspective transformation module that leverages activation maps from the YOLOv7 backbone to compute homographies using lines, intersection points, and ellipses. This method effectively adapts to dynamic and uncalibrated video data, even in viewpoints with limited visual information. In terms of performance, FootyVision sets new benchmarks. The model achieves a mean average precision (mAP) of 95.7% and an F1-score of 95.5% in object detection. For MOT, it demonstrates robust capabilities, with an IDF1 score of approximately 93% on both ISSIA and SoccerNet datasets. For SoccerNet, it reaches a MOTA of 94.04% and shows competitive results for ISSIA. Additionally, FootyVision scores a HOTA(0) of 93.1% and an overall HOTA of 72.16% for the SoccerNet dataset. Our ablation study confirms the effectiveness of the selected tracking features and identifies key attributes for further improvement. While the model excels in maintaining track accuracy throughout the testing dataset, we recognise the potential to enhance spatial-location accuracy.
Sohail Ahmed Khan; Duc-Tien Dang-Nguyen
CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection Conference
ACM International Conference on Multimedia Retrieval (ICMR), 2024.
Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links:
@conference{CLIpingSohail24,
title = {CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection},
author = {Sohail Ahmed Khan and Duc-Tien Dang-Nguyen},
url = {https://mediafutures.no/icmr24/},
year = {2024},
date = {2024-04-07},
booktitle = {ACM International Conference on Multimedia Retrieval (ICMR)},
journal = {ACM International Conference on Multimedia Retrieval (ICMR)},
abstract = {The recent advancements in Generative Adversarial Networks (GANs) and the emergence of Diffusion models have significantly streamlined the production of highly realistic and widely accessible synthetic content. As a result, there is a pressing need for effective general purpose detection mechanisms to mitigate the potential risks posed by deepfakes. In this paper, we explore the effectiveness of pre-trained vision-language models (VLMs) when paired with recent adaptation methods for universal deepfake detection. Following previous studies in this domain, we employ only a single dataset (ProGAN) in order to adapt CLIP for deepfake detection. However, in contrast to prior research, which rely solely on the visual part of CLIP while ignoring its textual component, our analysis reveals that retaining the text part is crucial. Consequently, the simple and lightweight Prompt Tuning based adaptation strategy that we employ outperforms the previous SOTA approach by 5.01% mAP and 6.61% accuracy while utilizing less than one third of the training data (200k images as compared to 720k). To assess the real-world applicability of our proposed models, we conduct a comprehensive evaluation across various scenarios. This involves rigorous testing on images sourced from 21 distinct datasets, including those generated by GANs-based, Diffusion-based and Commercial tools.},
keywords = {WP3: Media Content Production and Analysis},
pubstate = {published},
tppubtype = {conference}
}
The recent advancements in Generative Adversarial Networks (GANs) and the emergence of Diffusion models have significantly streamlined the production of highly realistic and widely accessible synthetic content. As a result, there is a pressing need for effective general purpose detection mechanisms to mitigate the potential risks posed by deepfakes. In this paper, we explore the effectiveness of pre-trained vision-language models (VLMs) when paired with recent adaptation methods for universal deepfake detection. Following previous studies in this domain, we employ only a single dataset (ProGAN) in order to adapt CLIP for deepfake detection. However, in contrast to prior research, which rely solely on the visual part of CLIP while ignoring its textual component, our analysis reveals that retaining the text part is crucial. Consequently, the simple and lightweight Prompt Tuning based adaptation strategy that we employ outperforms the previous SOTA approach by 5.01% mAP and 6.61% accuracy while utilizing less than one third of the training data (200k images as compared to 720k). To assess the real-world applicability of our proposed models, we conduct a comprehensive evaluation across various scenarios. This involves rigorous testing on images sourced from 21 distinct datasets, including those generated by GANs-based, Diffusion-based and Commercial tools.
Peter Andrews; Oda Elise Nordberg; Frode Guribye; Kazuyuki Fujita; Morten Fjeld; Njål Borch
AiCommentator: A Multimodal Conversational Agent for Embedded Visualization in Football Viewing Conference
Intelligent User Interfaces (IUI), 2024.
Abstract | BibTeX | Tags: WP4: Media Content Interaction and Accessibility | Links:
@conference{AIComment,
title = {AiCommentator: A Multimodal Conversational Agent for Embedded Visualization in Football Viewing},
author = {Peter Andrews and Oda Elise Nordberg and Frode Guribye and Kazuyuki Fujita and Morten Fjeld and Njål Borch},
url = {https://mediafutures.no/acm_iui_24_aicommentator_peterandrews-1/},
year = {2024},
date = {2024-03-18},
urldate = {2024-03-18},
booktitle = {Intelligent User Interfaces (IUI)},
journal = {Intelligent User Interfaces (IUI)},
abstract = {Traditionally, sports commentators provide viewers with diverse information, encompassing in-game developments and player performances. Yet young adult football viewers increasingly use mobile devices for deeper insights during football matches. Such insights into players on the pitch and performance statistics support viewers’ understanding of game stakes, creating a more engaging viewing experience. Inspired by commentators’ traditional roles and to incorporate information into a single platform, we developed AiCommentator, a Multimodal Conversational Agent (MCA) for embedded visualization and conversational interactions in football broadcast video. AiCommentator integrates embedded visualization, either with an automated non-interactive or with a responsive interactive commentary mode. Our system builds upon multimodal techniques, integrating computer vision and large language models, to demonstrate ways for designing tailored, interactive sports-viewing content. AiCommentator’s event system infers game states based on a multi-object tracking algorithm and computer vision backend, facilitating automated responsive commentary. We address three key topics: evaluating young adults’ satisfaction and immersion across the two viewing modes, enhancing viewer understanding of in-game events and players on the pitch, and devising methods to present this information in a usable manner. In a mixed-method evaluation (n=16) of AiCommentator, we found that the participants appreciated aspects of both system modes but preferred the interactive mode, expressing a higher degree of engagement and satisfaction. Our paper reports on our development of AiCommentator and presents the results from our user study, demonstrating the promise of interactive MCA for a more engaging sports viewing experience. Systems like AiCommentator could be pivotal in transforming the interactivity and accessibility of sports content, revolutionizing how sports viewers engage with video content.},
keywords = {WP4: Media Content Interaction and Accessibility},
pubstate = {published},
tppubtype = {conference}
}
Traditionally, sports commentators provide viewers with diverse information, encompassing in-game developments and player performances. Yet young adult football viewers increasingly use mobile devices for deeper insights during football matches. Such insights into players on the pitch and performance statistics support viewers’ understanding of game stakes, creating a more engaging viewing experience. Inspired by commentators’ traditional roles and to incorporate information into a single platform, we developed AiCommentator, a Multimodal Conversational Agent (MCA) for embedded visualization and conversational interactions in football broadcast video. AiCommentator integrates embedded visualization, either with an automated non-interactive or with a responsive interactive commentary mode. Our system builds upon multimodal techniques, integrating computer vision and large language models, to demonstrate ways for designing tailored, interactive sports-viewing content. AiCommentator’s event system infers game states based on a multi-object tracking algorithm and computer vision backend, facilitating automated responsive commentary. We address three key topics: evaluating young adults’ satisfaction and immersion across the two viewing modes, enhancing viewer understanding of in-game events and players on the pitch, and devising methods to present this information in a usable manner. In a mixed-method evaluation (n=16) of AiCommentator, we found that the participants appreciated aspects of both system modes but preferred the interactive mode, expressing a higher degree of engagement and satisfaction. Our paper reports on our development of AiCommentator and presents the results from our user study, demonstrating the promise of interactive MCA for a more engaging sports viewing experience. Systems like AiCommentator could be pivotal in transforming the interactivity and accessibility of sports content, revolutionizing how sports viewers engage with video content.
Johannes Kruse; Lien Michiels; Alain D. Starke; Nava Tintarev; Sanne Vrijenhoek
NORMalize: A Tutorial on the Normative Design and Evaluation of Information Access Systems Proceedings Article
In: CHIIR '24: Proceedings of the 2024 ACM SIGIR Conference on Human Information Interaction and Retrieval , 2024.
Abstract | BibTeX | Tags: NORMalize | Links:
@inproceedings{NORMalize24,
title = {NORMalize: A Tutorial on the Normative Design and Evaluation of Information Access Systems},
author = {Johannes Kruse and Lien Michiels and Alain D. Starke and Nava Tintarev and Sanne Vrijenhoek },
url = {https://mediafutures.no/chiir2024-normalize/},
year = {2024},
date = {2024-03-10},
urldate = {2024-03-10},
booktitle = {CHIIR '24: Proceedings of the 2024 ACM SIGIR Conference on Human Information Interaction and Retrieval
},
abstract = {Information access systems, such as Google News or YouTube, increasingly employ algorithms to rank diverse content such as music,
recipes, and news articles. Acknowledging the influential role of
these algorithms as gatekeepers to online content, the research
community is increasingly exploring ‘beyond-accuracy’ metrics.
However, deciding what norms and values are relevant and should
be prioritized when designing and evaluating information access
systems is a challenging task. This tutorial aims to cultivate normative thinking and decision-making in the design and evaluation
of information access systems. The tutorial comprises two key
components. The first part involves a lecture on the foundational
principles of normative thinking, emphasizing the importance of reflecting on the desired state of a system rather than its current state.
The second part is an interactive session where participants engage
in group discussions, applying normative thinking to a specific use
case. Participants analyze the system’s usage, stakeholders, and
relevant norms and values and address potential conflicts between
stakeholders and/or values. Through a point-allocation exercise,
participants represent stakeholders and advocate for specific values,
fostering a deeper understanding of normative decision-making in
the context of information access systems.},
keywords = {NORMalize},
pubstate = {published},
tppubtype = {inproceedings}
}
Information access systems, such as Google News or YouTube, increasingly employ algorithms to rank diverse content such as music,
recipes, and news articles. Acknowledging the influential role of
these algorithms as gatekeepers to online content, the research
community is increasingly exploring ‘beyond-accuracy’ metrics.
However, deciding what norms and values are relevant and should
be prioritized when designing and evaluating information access
systems is a challenging task. This tutorial aims to cultivate normative thinking and decision-making in the design and evaluation
of information access systems. The tutorial comprises two key
components. The first part involves a lecture on the foundational
principles of normative thinking, emphasizing the importance of reflecting on the desired state of a system rather than its current state.
The second part is an interactive session where participants engage
in group discussions, applying normative thinking to a specific use
case. Participants analyze the system’s usage, stakeholders, and
relevant norms and values and address potential conflicts between
stakeholders and/or values. Through a point-allocation exercise,
participants represent stakeholders and advocate for specific values,
fostering a deeper understanding of normative decision-making in
the context of information access systems.
recipes, and news articles. Acknowledging the influential role of
these algorithms as gatekeepers to online content, the research
community is increasingly exploring ‘beyond-accuracy’ metrics.
However, deciding what norms and values are relevant and should
be prioritized when designing and evaluating information access
systems is a challenging task. This tutorial aims to cultivate normative thinking and decision-making in the design and evaluation
of information access systems. The tutorial comprises two key
components. The first part involves a lecture on the foundational
principles of normative thinking, emphasizing the importance of reflecting on the desired state of a system rather than its current state.
The second part is an interactive session where participants engage
in group discussions, applying normative thinking to a specific use
case. Participants analyze the system’s usage, stakeholders, and
relevant norms and values and address potential conflicts between
stakeholders and/or values. Through a point-allocation exercise,
participants represent stakeholders and advocate for specific values,
fostering a deeper understanding of normative decision-making in
the context of information access systems.
Sanne Vrijenhoek; Lien Michiels; Johannes Kruse; Alain Starke; Jordi Viader Guerrero; Nava Tintarev
Report on NORMalize: The First Workshop on the Normative Design and Evaluation of Recommender Systems Proceedings Article
In: 2024.
Abstract | BibTeX | Tags: RecSys | Links:
@inproceedings{NormativeDeProceedings,
title = {Report on NORMalize: The First Workshop on the Normative Design and Evaluation of Recommender Systems},
author = {Sanne Vrijenhoek and Lien Michiels and Johannes Kruse and Alain Starke and Jordi Viader Guerrero and Nava Tintarev },
url = {https://mediafutures.no/preface-1/},
year = {2024},
date = {2024-02-13},
urldate = {2024-02-13},
abstract = {Recommender systems are among the most widely used applications of artificial intelligence. Because of their widespread use, it is important that practitioners and researchers think about the impact they may have on users, society, and other stakeholders. To that effect, the NORMalize workshop seeks to introduce normative thinking, to consider the norms and values that underpin recommender systems in the recommender systems community. The objective of NORMalize is to bring together a growing community of researchers and practitioners across disciplines who want to think about the norms and values that should be considered in the design and evaluation of recommender systems, and further educate them on how to reflect on, prioritise, and operationalise such norms and values. This document is a report on the first workshop, co-located with ACM RecSys ’23 in Singapore.
See also: https://ceur-ws.org/Vol-3639/},
keywords = {RecSys},
pubstate = {published},
tppubtype = {inproceedings}
}
Recommender systems are among the most widely used applications of artificial intelligence. Because of their widespread use, it is important that practitioners and researchers think about the impact they may have on users, society, and other stakeholders. To that effect, the NORMalize workshop seeks to introduce normative thinking, to consider the norms and values that underpin recommender systems in the recommender systems community. The objective of NORMalize is to bring together a growing community of researchers and practitioners across disciplines who want to think about the norms and values that should be considered in the design and evaluation of recommender systems, and further educate them on how to reflect on, prioritise, and operationalise such norms and values. This document is a report on the first workshop, co-located with ACM RecSys ’23 in Singapore.
See also: https://ceur-ws.org/Vol-3639/
See also: https://ceur-ws.org/Vol-3639/
Nicholas Diakopoulos; Christoph Trattner; Dietmar Jannach; Irene Costera Meijer; Enrico Motta
Leveraging Professional Ethics for Responsible AI: Applying AI techniques to journalism. Journal Article
In: Communications of the ACM, 2024.
BibTeX | Tags: Explainability | Links:
@article{leverag24,
title = {Leveraging Professional Ethics for Responsible AI: Applying AI techniques to journalism.},
author = {Nicholas Diakopoulos and Christoph Trattner and Dietmar Jannach and Irene Costera Meijer and Enrico Motta},
url = {https://mediafutures.no/3625252/https://mediafutures.no/3625252-1/},
year = {2024},
date = {2024-01-23},
urldate = {2024-01-23},
journal = {Communications of the ACM},
keywords = {Explainability},
pubstate = {published},
tppubtype = {article}
}
Peder Haugfos; John Magnus Ragnhildson Dahl; Jan Kratzer; Ines Wolf
Branding or visual storytelling? How legacy media use visual journalism to reach young people in the age of digitalization Journal Article
In: Journal of Applied Journalism & Media Studies, pp. 1-24, 2024.
Abstract | BibTeX | Tags: WP1: Understanding Media Experiences | Links:
@article{AJMS_FT_art_Dahl,
title = {Branding or visual storytelling? How legacy media use visual journalism to reach young people in the age of digitalization},
author = {Peder Haugfos and John Magnus Ragnhildson Dahl and Jan Kratzer and Ines Wolf},
url = {https://mediafutures.no/ajms_ft_art_dahl-3/},
year = {2024},
date = {2024-01-19},
urldate = {2024-01-19},
journal = {Journal of Applied Journalism & Media Studies},
pages = {1-24},
abstract = {This article discusses how legacy media companies are responding to the real or imagined
challenge of reaching young people in the age of digitalization, by investigating two different
strategies for how to make use of the so-called Generation Z’s preference for sensory
and visual journalism. Through expert interviews, we present how the Norwegian public
broadcaster NRK P3 and the biggest newspaper in Norway, VG, approach the challenge of
catching young people’s attention. We identify two strategies for how legacy media companies
work with visual expressions and designing their digital content when trying to reach
a wide, fragmented young target group on digital platforms. VG is a platform-oriented
storyteller where design is connected to the direction and mode of storytelling and tailored
to fit certain platforms. Their area of focus is being where their target groups are and
meeting the visual expectations of these audiences by taking cues from what is trending on
different platforms. NRK P3 takes the approach of a traditional brander that works in
both visionary and traditional ways to build a strong, trustworthy and visible brand. We
conclude by pointing out possible problems with both approaches.},
keywords = {WP1: Understanding Media Experiences},
pubstate = {published},
tppubtype = {article}
}
This article discusses how legacy media companies are responding to the real or imagined
challenge of reaching young people in the age of digitalization, by investigating two different
strategies for how to make use of the so-called Generation Z’s preference for sensory
and visual journalism. Through expert interviews, we present how the Norwegian public
broadcaster NRK P3 and the biggest newspaper in Norway, VG, approach the challenge of
catching young people’s attention. We identify two strategies for how legacy media companies
work with visual expressions and designing their digital content when trying to reach
a wide, fragmented young target group on digital platforms. VG is a platform-oriented
storyteller where design is connected to the direction and mode of storytelling and tailored
to fit certain platforms. Their area of focus is being where their target groups are and
meeting the visual expectations of these audiences by taking cues from what is trending on
different platforms. NRK P3 takes the approach of a traditional brander that works in
both visionary and traditional ways to build a strong, trustworthy and visible brand. We
conclude by pointing out possible problems with both approaches.
challenge of reaching young people in the age of digitalization, by investigating two different
strategies for how to make use of the so-called Generation Z’s preference for sensory
and visual journalism. Through expert interviews, we present how the Norwegian public
broadcaster NRK P3 and the biggest newspaper in Norway, VG, approach the challenge of
catching young people’s attention. We identify two strategies for how legacy media companies
work with visual expressions and designing their digital content when trying to reach
a wide, fragmented young target group on digital platforms. VG is a platform-oriented
storyteller where design is connected to the direction and mode of storytelling and tailored
to fit certain platforms. Their area of focus is being where their target groups are and
meeting the visual expectations of these audiences by taking cues from what is trending on
different platforms. NRK P3 takes the approach of a traditional brander that works in
both visionary and traditional ways to build a strong, trustworthy and visible brand. We
conclude by pointing out possible problems with both approaches.
2023
Erik Knudsen
Modeling news recommender systems’ conditional effects on selective exposure: evidence from two online experiments Best Paper Journal Article
In: Journal of Communication , 2023.
Abstract | BibTeX | Tags: WP1: Understanding Media Experiences | Links:
@article{nokey,
title = {Modeling news recommender systems’ conditional effects on selective exposure: evidence from two online experiments},
author = {Erik Knudsen},
url = {https://mediafutures.no/jqac047/},
year = {2023},
date = {2023-12-23},
urldate = {2023-12-23},
journal = {Journal of Communication },
abstract = {Under which conditions do news recommender systems (NRSs) amplify or reduce selective exposure? I provide the Recommender Influenced Selective Exposure framework, which aims to enable researchers to model and study the conditional effects of NRSs on selective exposure. I empirically test this framework by studying user behavior on a news site where the choice environment is designed to systematically influence selective exposure. Through two preregistered online experiments that simulate different NRSs and unobtrusively log user behavior, I contribute empirical evidence that an NRS can increase or decrease the chance that selective exposure occurs, depending on what the NRS is designed to achieve. These insights have implications for ongoing scholarly debates on the democratic impact of NRSs.},
keywords = {WP1: Understanding Media Experiences},
pubstate = {published},
tppubtype = {article}
}
Under which conditions do news recommender systems (NRSs) amplify or reduce selective exposure? I provide the Recommender Influenced Selective Exposure framework, which aims to enable researchers to model and study the conditional effects of NRSs on selective exposure. I empirically test this framework by studying user behavior on a news site where the choice environment is designed to systematically influence selective exposure. Through two preregistered online experiments that simulate different NRSs and unobtrusively log user behavior, I contribute empirical evidence that an NRS can increase or decrease the chance that selective exposure occurs, depending on what the NRS is designed to achieve. These insights have implications for ongoing scholarly debates on the democratic impact of NRSs.
Bahareh Fatemi; Fazle Rabbi; Andreas L. Opdahl
Evaluating the Effectiveness of GPT Large Language Model for News Classification in the IPTC News Ontology Journal Article
In: IEEE Access, 2023.
Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links:
@article{GPTLangMo,
title = {Evaluating the Effectiveness of GPT Large Language Model for News Classification in the IPTC News Ontology},
author = {Bahareh Fatemi and Fazle Rabbi and Andreas L. Opdahl },
url = {https://mediafutures.no/evaluating_the_effectiveness_of_gpt_large_language_model_for_news_classification_in_the_iptc_news_ontology/},
year = {2023},
date = {2023-12-21},
journal = {IEEE Access},
abstract = {News classification plays a vital role in newsrooms, as it involves the time-consuming task
of categorizing news articles and requires domain knowledge. Effective news classification is essential
for categorizing and organizing a constant flow of information, serving as the foundation for subsequent
tasks, such as news aggregation, monitoring, filtering, and organization. The automation of this process can
significantly benefit newsrooms by saving time and resources. In this study, we explore the potential of the
GPT large language model in a zero-shot setting for multi-class classification of news articles within the
widely accepted International Press Telecommunications Council (IPTC) news ontology. The IPTC news
ontology provides a structured framework for categorizing news, facilitating the efficient organization and
retrieval of news content. By investigating the effectiveness of the GPT language model in this classification
task, we aimed to understand its capabilities and potential applications in the news domain. This study was
conducted as part of our ongoing research in the field of automated journalism.},
keywords = {WP3: Media Content Production and Analysis},
pubstate = {published},
tppubtype = {article}
}
News classification plays a vital role in newsrooms, as it involves the time-consuming task
of categorizing news articles and requires domain knowledge. Effective news classification is essential
for categorizing and organizing a constant flow of information, serving as the foundation for subsequent
tasks, such as news aggregation, monitoring, filtering, and organization. The automation of this process can
significantly benefit newsrooms by saving time and resources. In this study, we explore the potential of the
GPT large language model in a zero-shot setting for multi-class classification of news articles within the
widely accepted International Press Telecommunications Council (IPTC) news ontology. The IPTC news
ontology provides a structured framework for categorizing news, facilitating the efficient organization and
retrieval of news content. By investigating the effectiveness of the GPT language model in this classification
task, we aimed to understand its capabilities and potential applications in the news domain. This study was
conducted as part of our ongoing research in the field of automated journalism.
of categorizing news articles and requires domain knowledge. Effective news classification is essential
for categorizing and organizing a constant flow of information, serving as the foundation for subsequent
tasks, such as news aggregation, monitoring, filtering, and organization. The automation of this process can
significantly benefit newsrooms by saving time and resources. In this study, we explore the potential of the
GPT large language model in a zero-shot setting for multi-class classification of news articles within the
widely accepted International Press Telecommunications Council (IPTC) news ontology. The IPTC news
ontology provides a structured framework for categorizing news, facilitating the efficient organization and
retrieval of news content. By investigating the effectiveness of the GPT language model in this classification
task, we aimed to understand its capabilities and potential applications in the news domain. This study was
conducted as part of our ongoing research in the field of automated journalism.
Sohail Ahmed Khan; Duc-Tien Dang-Nguyen
Deepfake Detection: Analysing Model Generalisation Across Architectures, Datasets and Pre-Training Paradigms Conference
IEEE Access, 2023.
Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links:
@conference{deepfakede,
title = {Deepfake Detection: Analysing Model Generalisation Across Architectures, Datasets and Pre-Training Paradigms},
author = {Sohail Ahmed Khan and Duc-Tien Dang-Nguyen},
url = {https://mediafutures.no/ieee_access_2023___deepfake_comparative_analysis/},
year = {2023},
date = {2023-12-15},
booktitle = {IEEE Access},
abstract = {As deepfake technology gains traction, the need for reliable detection systems is crucial. Recent research has introduced various deep learning-based detection systems, yet they exhibit limitations in generalizing effectively across diverse data distributions that differ from the training data. Our study focuses on understanding the generalization challenges by exploring specific aspects such as deep learning model architecture, pre-training strategy and datasets. Through a comprehensive comparative analysis, we evaluate multiple supervised and self-supervised deep learning models for deepfake detection.
Specifically, we evaluate eight supervised deep learning architectures and two transformer-based models pre-trained using self-supervised strategies (DINO, CLIP) on four different deepfake detection benchmarks (FakeAVCeleb, CelebDF-V2, DFDC and FaceForensics++). Our analysis includes intra-dataset and inter-dataset evaluations, examining the best performing models, generalisation capabilities and impact of augmentations. We also investigate the trade-off between model size, efficiency and performance. Our main goal is to provide insights into the effectiveness of different deep learning architectures (transformers, CNNs), training strategies (supervised, self-supervised) and deepfake detection benchmarks. Through our extensive analysis, we established that Transformer models outperform CNN models in deepfake detection. Also, we show that FaceForensics++ and DFDC datasets equip models with comparably better generalisation capabilities, as compared to FakeAVCeleb and CelebDF-V2 datasets. Our analysis also show that image augmentations can be helpful in achieving better performance, at least for the Transformer models.},
keywords = {WP3: Media Content Production and Analysis},
pubstate = {published},
tppubtype = {conference}
}
As deepfake technology gains traction, the need for reliable detection systems is crucial. Recent research has introduced various deep learning-based detection systems, yet they exhibit limitations in generalizing effectively across diverse data distributions that differ from the training data. Our study focuses on understanding the generalization challenges by exploring specific aspects such as deep learning model architecture, pre-training strategy and datasets. Through a comprehensive comparative analysis, we evaluate multiple supervised and self-supervised deep learning models for deepfake detection.
Specifically, we evaluate eight supervised deep learning architectures and two transformer-based models pre-trained using self-supervised strategies (DINO, CLIP) on four different deepfake detection benchmarks (FakeAVCeleb, CelebDF-V2, DFDC and FaceForensics++). Our analysis includes intra-dataset and inter-dataset evaluations, examining the best performing models, generalisation capabilities and impact of augmentations. We also investigate the trade-off between model size, efficiency and performance. Our main goal is to provide insights into the effectiveness of different deep learning architectures (transformers, CNNs), training strategies (supervised, self-supervised) and deepfake detection benchmarks. Through our extensive analysis, we established that Transformer models outperform CNN models in deepfake detection. Also, we show that FaceForensics++ and DFDC datasets equip models with comparably better generalisation capabilities, as compared to FakeAVCeleb and CelebDF-V2 datasets. Our analysis also show that image augmentations can be helpful in achieving better performance, at least for the Transformer models.
Specifically, we evaluate eight supervised deep learning architectures and two transformer-based models pre-trained using self-supervised strategies (DINO, CLIP) on four different deepfake detection benchmarks (FakeAVCeleb, CelebDF-V2, DFDC and FaceForensics++). Our analysis includes intra-dataset and inter-dataset evaluations, examining the best performing models, generalisation capabilities and impact of augmentations. We also investigate the trade-off between model size, efficiency and performance. Our main goal is to provide insights into the effectiveness of different deep learning architectures (transformers, CNNs), training strategies (supervised, self-supervised) and deepfake detection benchmarks. Through our extensive analysis, we established that Transformer models outperform CNN models in deepfake detection. Also, we show that FaceForensics++ and DFDC datasets equip models with comparably better generalisation capabilities, as compared to FakeAVCeleb and CelebDF-V2 datasets. Our analysis also show that image augmentations can be helpful in achieving better performance, at least for the Transformer models.
Fazle Rabbi; Bahareh Fatemi; Yngve Lamo; Andreas L. Opdahl
A model-based framework for NEWS content analysis Journal Article
In: 12th International Conference on Model-Based Software and Systems Engineering, 2023.
Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links:
@article{modelBased23,
title = {A model-based framework for NEWS content analysis},
author = {Fazle Rabbi and Bahareh Fatemi and Yngve Lamo and Andreas L. Opdahl},
url = {https://mediafutures.no/news-content-analysis/},
year = {2023},
date = {2023-12-12},
urldate = {2023-12-12},
journal = {12th International Conference on Model-Based Software and Systems Engineering},
abstract = {News articles are published all over the world to cover important events. Journalists need to keep track of
ongoing events in a fair and accountable manner and analyze them for newsworthiness. It requires enormous
amount of time for journalists to process information coming from main stream news media, social media
from all over the world as well as policy and law circulated by governments and international organizations.
News articles published by different news providers may consist of subjectivity of the reporters due to the
influence of reporters’ backgrounds, world views and opinions. In today’s practice of journalism there is a
lack of computational methods to support journalists to investigate fairness and monitor and analyze large
massive information streams. In this paper we present a model based approach to analyze the perspectives of
news publishers and monitor the progression of news events from various perspective. The domain concepts
in the news domain such as the news events and their contextual information is represented across various
dimensions in a knowledge graph. We presented a multi dimensional comparative analysis method of news
events for analyzing news article variants and for uncovering underlying storylines. To show the applicability
of the proposed method in real life, we demonstrated a running example in this paper. The utilization of
a model-based approach ensures the adaptability of our proposed method for representing a wide array of
domain concepts within the news domain.},
keywords = {WP3: Media Content Production and Analysis},
pubstate = {published},
tppubtype = {article}
}
News articles are published all over the world to cover important events. Journalists need to keep track of
ongoing events in a fair and accountable manner and analyze them for newsworthiness. It requires enormous
amount of time for journalists to process information coming from main stream news media, social media
from all over the world as well as policy and law circulated by governments and international organizations.
News articles published by different news providers may consist of subjectivity of the reporters due to the
influence of reporters’ backgrounds, world views and opinions. In today’s practice of journalism there is a
lack of computational methods to support journalists to investigate fairness and monitor and analyze large
massive information streams. In this paper we present a model based approach to analyze the perspectives of
news publishers and monitor the progression of news events from various perspective. The domain concepts
in the news domain such as the news events and their contextual information is represented across various
dimensions in a knowledge graph. We presented a multi dimensional comparative analysis method of news
events for analyzing news article variants and for uncovering underlying storylines. To show the applicability
of the proposed method in real life, we demonstrated a running example in this paper. The utilization of
a model-based approach ensures the adaptability of our proposed method for representing a wide array of
domain concepts within the news domain.
ongoing events in a fair and accountable manner and analyze them for newsworthiness. It requires enormous
amount of time for journalists to process information coming from main stream news media, social media
from all over the world as well as policy and law circulated by governments and international organizations.
News articles published by different news providers may consist of subjectivity of the reporters due to the
influence of reporters’ backgrounds, world views and opinions. In today’s practice of journalism there is a
lack of computational methods to support journalists to investigate fairness and monitor and analyze large
massive information streams. In this paper we present a model based approach to analyze the perspectives of
news publishers and monitor the progression of news events from various perspective. The domain concepts
in the news domain such as the news events and their contextual information is represented across various
dimensions in a knowledge graph. We presented a multi dimensional comparative analysis method of news
events for analyzing news article variants and for uncovering underlying storylines. To show the applicability
of the proposed method in real life, we demonstrated a running example in this paper. The utilization of
a model-based approach ensures the adaptability of our proposed method for representing a wide array of
domain concepts within the news domain.
Find us
Lars Hilles gate 30
5008 Bergen
Norway
Contact us
MediaFutures
Office@mediafutures.no
Responsible Editor:
Centre Director Prof. Dr. Christoph Trattner
Christoph.Trattner@uib.no
Hosted by
PARTNERS
CLUSTER
FUNDED BY
To learn more about the University of Bergen's cookie policy, see the link below.
Copyright © University of Bergen 2024