2021
|
| VXSlate: Exploring Combination of Head Movements and Mobile Touch for Large Virtual Display Interaction Proceeding Khanh-Duy Le; Tanh Quang Tran; Karol Chlasta; Krzysztof Krejtz; Morten Fjeld; Andreas Kunz Association for Computing Machinery, New York, NY, USA, 2021, ISBN: 978-1-4503-8476-6. @proceedings{Kunz2021,
title = {VXSlate: Exploring Combination of Head Movements and Mobile Touch for Large Virtual Display Interaction},
author = {Khanh-Duy Le and Tanh Quang Tran and Karol Chlasta and Krzysztof Krejtz and Morten Fjeld and Andreas Kunz},
doi = {https://doi.org/10.1145/3461778.3462076},
isbn = {978-1-4503-8476-6},
year = {2021},
date = {2021-06-28},
journal = {DIS '21: Designing Interactive Systems Conference 2021},
pages = {283–297},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
keywords = {WP4: Media Content Interaction and Accessibility},
pubstate = {published},
tppubtype = {proceedings}
}
|
| Conversational Futures: Emancipating Conversational Interactions for Futures Worth Wanting Conference Minha Lee; Renee Noortman; Cristina Zaga; Alain D. Starke; Gijs Huisman; Kristina Andersen no. May 2021, 2021. @conference{Lee2021,
title = {Conversational Futures: Emancipating Conversational Interactions for Futures Worth Wanting},
author = {Minha Lee and Renee Noortman and Cristina Zaga and Alain D. Starke and Gijs Huisman and Kristina Andersen},
url = {https://minha-lee.github.io/files/mlee_Conversational_Futures_CHI2021.pdf},
year = {2021},
date = {2021-05-13},
number = {May 2021},
pages = {1-13},
abstract = {We present a vision for conversational user interfaces (CUIs) asprobes forspeculating with, rather than as objects to speculateabout. Popular CUIs, e.g., Alexa, are changing the way we converse,narrate, and imagine the world(s) to come. Yet, current conversa-tional interactions normatively may promote non-desirable ends,delivering a restricted range of request-response interactions withsexist and digital colonialist tendencies. Our critical design ap-proach envisions alternatives by considering how future voices canreside in CUIs as enabling probes. We present novel explorationsthat illustrate the potential of CUIs as critical design material, bycritiquing present norms and conversing with imaginary species.As micro-level interventions, we show that conversationswithdi-verse futuresthroughCUIs can persuade us to critically shape ourdiscourse on macro-scale concerns of the present, e.g., sustainabil-ity. We reflect on how conversational interactions with pluralistic,imagined futures can contribute to howbeing humanstands tochange.},
keywords = {Conversational user interfaces, critical design, design fiction, futuring, speculative design},
pubstate = {published},
tppubtype = {conference}
}
We present a vision for conversational user interfaces (CUIs) asprobes forspeculating with, rather than as objects to speculateabout. Popular CUIs, e.g., Alexa, are changing the way we converse,narrate, and imagine the world(s) to come. Yet, current conversa-tional interactions normatively may promote non-desirable ends,delivering a restricted range of request-response interactions withsexist and digital colonialist tendencies. Our critical design ap-proach envisions alternatives by considering how future voices canreside in CUIs as enabling probes. We present novel explorationsthat illustrate the potential of CUIs as critical design material, bycritiquing present norms and conversing with imaginary species.As micro-level interventions, we show that conversationswithdi-verse futuresthroughCUIs can persuade us to critically shape ourdiscourse on macro-scale concerns of the present, e.g., sustainabil-ity. We reflect on how conversational interactions with pluralistic,imagined futures can contribute to howbeing humanstands tochange. |
| Nudging Healthy Choices in Food Search Through Visual Attractiveness Journal Article Alain D. Starke; Martijn C. Willemsen; Christoph Trattner In: no. April 2021, pp. 1-18, 2021. @article{Starke2021,
title = {Nudging Healthy Choices in Food Search Through Visual Attractiveness},
author = {Alain D. Starke and Martijn C. Willemsen and Christoph Trattner},
url = {https://www.frontiersin.org/articles/10.3389/frai.2021.621743/full},
doi = {10.3389/frai.2021.621743},
year = {2021},
date = {2021-04-22},
number = {April 2021},
pages = {1-18},
abstract = {Recipe websites are becoming increasingly popular to support people in their home cooking. However, most of these websites prioritize popular recipes, which tend to be unhealthy. Drawing upon research on visual biases and nudges, this paper investigates whether healthy food choices can be supported in food search by depicting attractive images alongside recipes, as well as by re-ranking search results on health. After modelling the visual attractiveness of recipe images, we asked 239 users to search for specific online recipes and to select those they liked the most. Our analyses revealed that users tended to choose a healthier recipe if a visually attractive image was depicted alongside it, as well as if it was listed at the top of a list of search results. Even though less popular recipes were promoted this way, it did not come at the cost of a user’s level of satisfaction},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {article}
}
Recipe websites are becoming increasingly popular to support people in their home cooking. However, most of these websites prioritize popular recipes, which tend to be unhealthy. Drawing upon research on visual biases and nudges, this paper investigates whether healthy food choices can be supported in food search by depicting attractive images alongside recipes, as well as by re-ranking search results on health. After modelling the visual attractiveness of recipe images, we asked 239 users to search for specific online recipes and to select those they liked the most. Our analyses revealed that users tended to choose a healthier recipe if a visually attractive image was depicted alongside it, as well as if it was listed at the top of a list of search results. Even though less popular recipes were promoted this way, it did not come at the cost of a user’s level of satisfaction |
| Exploring Multi-List User Interfaces for Similar-Item Recommendations Conference Dietmar Jannach; Mathias Jesse; Michael Jugovac; Christoph Trattner 29th ACM International Conference on User Modeling, Adaptation and Personalization (UMAP '21) 2021. @conference{Jannach2021,
title = {Exploring Multi-List User Interfaces for Similar-Item Recommendations},
author = {Dietmar Jannach and Mathias Jesse and Michael Jugovac and Christoph Trattner},
url = {https://mediafutures.no/conference_umap_2021-2/},
year = {2021},
date = {2021-03-26},
organization = {29th ACM International Conference on User Modeling, Adaptation and Personalization (UMAP '21)},
abstract = {On many e-commerce and media streaming sites, the user inter-face (UI) consists of multiple lists of item suggestions. The itemsin each list are usually chosen based on pre-defined strategies and,e.g., show movies of the same genre or category. Such interfacesare common in practice, but there is almost no academic researchregarding the optimal design and arrangement of such multi-listUIs for recommenders. In this paper, we report the results of anexploratory user study that examined the effects of various designalternatives on the decision-making behavior of users in the con-text of similar-item recommendations. Our investigations showed,among other aspects, that decision-making is slower and more de-manding with multi-list interfaces, but that users also explore moreoptions before making a decision. Regarding the selection of thealgorithm to retrieve similar items, our study furthermore revealsthe importance of considering social-based similarity measures.},
keywords = {Recommender system, User Interface, User Study},
pubstate = {published},
tppubtype = {conference}
}
On many e-commerce and media streaming sites, the user inter-face (UI) consists of multiple lists of item suggestions. The itemsin each list are usually chosen based on pre-defined strategies and,e.g., show movies of the same genre or category. Such interfacesare common in practice, but there is almost no academic researchregarding the optimal design and arrangement of such multi-listUIs for recommenders. In this paper, we report the results of anexploratory user study that examined the effects of various designalternatives on the decision-making behavior of users in the con-text of similar-item recommendations. Our investigations showed,among other aspects, that decision-making is slower and more de-manding with multi-list interfaces, but that users also explore moreoptions before making a decision. Regarding the selection of thealgorithm to retrieve similar items, our study furthermore revealsthe importance of considering social-based similarity measures. |
| Automatiske nyhende Online Lars Nyre; Bjørnar Tessem Dag og Tid 2021, visited: 26.03.2021. @online{Tessem2021,
title = {Automatiske nyhende},
author = {Lars Nyre and Bjørnar Tessem},
url = {https://www.dagogtid.no/feature/automatiske-nyhende-6.3.20626.2396ffd8e5},
year = {2021},
date = {2021-03-26},
urldate = {2021-03-26},
journal = {Dag og Tid},
number = {12},
organization = {Dag og Tid},
keywords = {WP3: Media Content Production and Analysis},
pubstate = {published},
tppubtype = {online}
}
|
| VXSlate: Combining Head Movement and Mobile Touch for Large Virtual Display Interaction Conference Khanh-Duy Le; Tanh Quang Tran; Karol Chlasta; Krzysztof Krejtz; Morten Fjeld; Andreas Kunz 2021 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW). IEEE The Institute of Electrical and Electronics Engineers, Inc., 2021. @conference{Le2021b,
title = {VXSlate: Combining Head Movement and Mobile Touch for Large Virtual Display Interaction},
author = {Khanh-Duy Le and Tanh Quang Tran and Karol Chlasta and Krzysztof Krejtz and Morten Fjeld and Andreas Kunz},
url = {https://conferences.computer.org/vrpub/pdfs/VRW2021-2ANNoldm4A10Ml9f63uYC9/136700a528/136700a528.pdf
https://www.youtube.com/watch?v=N8ZJlKWj4mk&ab_channel=DuyL%C3%AAKh%C3%A1nh},
doi = { 10.1109/VRW52623.2021.00146},
year = {2021},
date = {2021-02-12},
pages = {528-529},
publisher = {IEEE The Institute of Electrical and Electronics Engineers, Inc.},
organization = {2021 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW).},
abstract = {Virtual Reality (VR) headsets can open opportunities for users to accomplish complex tasks on large virtual displays, using compact setups. However, interacting with large virtual displays using existing interaction techniques might cause fatigue, especially for precise manipulations, due to the lack of physical surfaces. We designed VXSlate, an interaction technique that uses a large virtual display, as an expansion of a tablet. VXSlate combines a user’s head movements, as tracked by the VR headset, and touch interaction on the tablet. The user’s head movements position both a virtual representation of the tablet and of the user’s hand on the large virtual display. The user’s multi-touch interactions perform finely-tuned content manipulations.},
keywords = {Human computer interaction, Human-centered computing, Interaction techniques, SFI MediaFutures, Virtual Reality, WP4: Media Content Interaction and Accessibility},
pubstate = {published},
tppubtype = {conference}
}
Virtual Reality (VR) headsets can open opportunities for users to accomplish complex tasks on large virtual displays, using compact setups. However, interacting with large virtual displays using existing interaction techniques might cause fatigue, especially for precise manipulations, due to the lack of physical surfaces. We designed VXSlate, an interaction technique that uses a large virtual display, as an expansion of a tablet. VXSlate combines a user’s head movements, as tracked by the VR headset, and touch interaction on the tablet. The user’s head movements position both a virtual representation of the tablet and of the user’s hand on the large virtual display. The user’s multi-touch interactions perform finely-tuned content manipulations. |
| Framing Protest in Online News and Readers’ Comments: The Case of Serbian Protest “Against Dictatorship” Journal Article Jelena Kleut; Ana Milojevic In: International Journal of Communication, vol. 15, no. 21, pp. 82-102, 2021, (Pre SFI). @article{Kleut2021,
title = {Framing Protest in Online News and Readers’ Comments: The Case of Serbian Protest “Against Dictatorship”},
author = {Jelena Kleut and Ana Milojevic},
url = {https://www.researchgate.net/publication/348787747_Framing_Protest_in_Online_News_and_Readers\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\'_Comments_The_Case_of_Serbian_Protest_Against_Dictatorship},
year = {2021},
date = {2021-01-01},
journal = {International Journal of Communication},
volume = {15},
number = {21},
pages = {82-102},
series = {Not connected to SFI MediaFutures},
abstract = {This research examines the "protest paradigm" in the digital news environment of a politically polarized media system by considering relations between news and online readers' comments about the Serbian protest Against Dictatorship, which was held in 2017. Applying content analysis to news and comments from two news websites, our study indicates the need to account for opposing framing of the protest (violence/peacefulness, de/legitimizing and un/democratic) in a polarized environment. The results show that the distribution of opposing frames is guided by the media relations with the government. Online readers' comments generally enhance this polarized pattern of frame distribution, with the exception of the performance frame, which remains prolific in the media, but absent from readers' comments.},
note = {Pre SFI},
keywords = {framing, Online Media, polarized media system, protest paradigm, user comments, WP1: Understanding Media Experiences},
pubstate = {published},
tppubtype = {article}
}
This research examines the "protest paradigm" in the digital news environment of a politically polarized media system by considering relations between news and online readers' comments about the Serbian protest Against Dictatorship, which was held in 2017. Applying content analysis to news and comments from two news websites, our study indicates the need to account for opposing framing of the protest (violence/peacefulness, de/legitimizing and un/democratic) in a polarized environment. The results show that the distribution of opposing frames is guided by the media relations with the government. Online readers' comments generally enhance this polarized pattern of frame distribution, with the exception of the performance frame, which remains prolific in the media, but absent from readers' comments. |
| Auka røynd (AR) Medium Lars Nyre; Bjørnar Tessem Dag og Tid, 2021. @media{cristin1894361,
title = {Auka røynd (AR)},
author = {Lars Nyre and Bjørnar Tessem},
url = {https://app.cristin.no/results/show.jsf?id=1894361, Cristin},
year = {2021},
date = {2021-01-01},
howpublished = {Dag og Tid},
keywords = {Cristin},
pubstate = {published},
tppubtype = {media}
}
|
| Ting i internettet Medium Lars Nyre; Bjørnar Tessem Dag og Tid, 2021. @media{cristin1931531,
title = {Ting i internettet},
author = {Lars Nyre and Bjørnar Tessem},
url = {https://app.cristin.no/results/show.jsf?id=1931531, Cristin},
year = {2021},
date = {2021-01-01},
howpublished = {Dag og Tid},
keywords = {Cristin},
pubstate = {published},
tppubtype = {media}
}
|
| Automatiske nyhende Medium Lars Nyre; Bjørnar Tessem Dag og Tid, 2021. @media{cristin1905817,
title = {Automatiske nyhende},
author = {Lars Nyre and Bjørnar Tessem},
url = {https://app.cristin.no/results/show.jsf?id=1905817, Cristin},
year = {2021},
date = {2021-01-01},
howpublished = {Dag og Tid},
keywords = {Cristin},
pubstate = {published},
tppubtype = {media}
}
|
| EN ANALYSE AV SAMMENHENGEN MELLOM BRUK AV NRKS DIGITALE NYHETSTILBUD OG BETALINGSVILJE FOR DIGITALE NYHETER Technical Report Erik Knudsen; Hallvard Moe 2021. @techreport{cristin1958452,
title = {EN ANALYSE AV SAMMENHENGEN MELLOM BRUK AV NRKS DIGITALE NYHETSTILBUD OG BETALINGSVILJE FOR DIGITALE NYHETER},
author = {Erik Knudsen and Hallvard Moe},
url = {https://app.cristin.no/results/show.jsf?id=1958452, Cristin},
year = {2021},
date = {2021-01-01},
keywords = {Cristin},
pubstate = {published},
tppubtype = {techreport}
}
|
| Using Gender- and Polarity-informed Models to Investigate Bias Working paper Samia Touileb; Lilja Øvrelid; Erik Velldal 2021. @workingpaper{cristin1958571,
title = {Using Gender- and Polarity-informed Models to Investigate Bias},
author = {Samia Touileb and Lilja Øvrelid and Erik Velldal},
url = {https://app.cristin.no/results/show.jsf?id=1958571, Cristin},
year = {2021},
date = {2021-01-01},
keywords = {Cristin},
pubstate = {published},
tppubtype = {workingpaper}
}
|
| Novel Methods Using Human Emotion and Visual Features for Recommending Movies Masters Thesis Mehdi Elahi; Øyvind Johannessen Universitetet i Bergen, 2021. @mastersthesis{cristin1957008,
title = {Novel Methods Using Human Emotion and Visual Features for Recommending Movies},
author = {Mehdi Elahi and Øyvind Johannessen},
url = {https://app.cristin.no/results/show.jsf?id=1957008, Cristin},
year = {2021},
date = {2021-01-01},
school = {Universitetet i Bergen},
abstract = {This master thesis investigates novel methods using human emotion as contextual information to estimate and elicit ratings when watching movie trailers. The aim is to acquire user preferences without the intrusive and time-consuming behavior of Explicit Feedback strategies, and generate quality recommendations. The proposed preference-elicitation technique is implemented as an Emotion-based Filtering technique (EF) to generate recommendations, and is evaluated against two other recommendation techniques. One Visual-based Filtering technique, using low-level visual features of movies, and one Collaborative Filtering (CF) using explicit ratings. In terms of Accuracy, we found the Emotion-based Filtering technique (EF) to perform better than the two other filtering techniques. In terms of Diversity, the Visual-based Filtering (VF) performed best. We further analyse the obtained data to see if movie genres tend to induce specific emotions, and the potential correlation between emotional responses of users and visual features of movie trailers. When investigating emotional responses, we found that joy and disgust tend to be more prominent in movie genres than other emotions. Our findings also suggest potential correlations on a per movie level. The proposed Emotion-based Filtering technique can be adopted as an Implicit Feedback strategy to obtain user preferences. For future work, we will extend the experiment with more participants and build stronger affective profiles to be studied when recommending movies.},
keywords = {Cristin},
pubstate = {published},
tppubtype = {mastersthesis}
}
This master thesis investigates novel methods using human emotion as contextual information to estimate and elicit ratings when watching movie trailers. The aim is to acquire user preferences without the intrusive and time-consuming behavior of Explicit Feedback strategies, and generate quality recommendations. The proposed preference-elicitation technique is implemented as an Emotion-based Filtering technique (EF) to generate recommendations, and is evaluated against two other recommendation techniques. One Visual-based Filtering technique, using low-level visual features of movies, and one Collaborative Filtering (CF) using explicit ratings. In terms of Accuracy, we found the Emotion-based Filtering technique (EF) to perform better than the two other filtering techniques. In terms of Diversity, the Visual-based Filtering (VF) performed best. We further analyse the obtained data to see if movie genres tend to induce specific emotions, and the potential correlation between emotional responses of users and visual features of movie trailers. When investigating emotional responses, we found that joy and disgust tend to be more prominent in movie genres than other emotions. Our findings also suggest potential correlations on a per movie level. The proposed Emotion-based Filtering technique can be adopted as an Implicit Feedback strategy to obtain user preferences. For future work, we will extend the experiment with more participants and build stronger affective profiles to be studied when recommending movies. |
| Unify Media and UX with timed variables Working paper Ingar M Arntzen; Njål Borch; Anders Andersen 2021. @workingpaper{cristin1959749,
title = {Unify Media and UX with timed variables},
author = {Ingar M Arntzen and Njål Borch and Anders Andersen},
url = {https://app.cristin.no/results/show.jsf?id=1959749, Cristin},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
keywords = {Cristin},
pubstate = {published},
tppubtype = {workingpaper}
}
|
| Video Recommendations Based on Visual Features Extracted with Deep Learning Masters Thesis Mehdi Elahi; Tord Kvifte Universitetet i Bergen, 2021. @mastersthesis{cristin1956990,
title = {Video Recommendations Based on Visual Features Extracted with Deep Learning},
author = {Mehdi Elahi and Tord Kvifte},
url = {https://app.cristin.no/results/show.jsf?id=1956990, Cristin
https://hdl.handle.net/11250/2760300},
year = {2021},
date = {2021-01-01},
school = {Universitetet i Bergen},
abstract = {When a movie is uploaded to a movie Recommender System (e.g., YouTube), the system can exploit various forms of descriptive features (e.g., tags and genre) in order to generate personalized recommendation for users. However, there are situations where the descriptive features are missing or very limited and the system may fail to include such a movie in the recommendation list, known as Cold-start problem. This thesis investigates recommendation based on a novel form of content features, extracted from movies, in order to generate recommendation for users. Such features represent the visual aspects of movies, based on Deep Learning models, and hence, do not require any human annotation when extracted. The proposed technique has been evaluated in both offline and online evaluations using a large dataset of movies. The online evaluation has been carried out in a evaluation framework developed for this thesis. Results from the offline and online evaluation (N=150) show that automatically extracted visual features can mitigate the cold-start problem by generating recommendation with a superior quality compared to different baselines, including recommendation based on human-annotated features. The results also point to subtitles as a high-quality future source of automatically extracted features. The visual feature dataset, named DeepCineProp13K and the subtitle dataset, CineSub3K, as well as the proposed evaluation framework are all made openly available online in a designated Github repository.},
keywords = {Cristin},
pubstate = {published},
tppubtype = {mastersthesis}
}
When a movie is uploaded to a movie Recommender System (e.g., YouTube), the system can exploit various forms of descriptive features (e.g., tags and genre) in order to generate personalized recommendation for users. However, there are situations where the descriptive features are missing or very limited and the system may fail to include such a movie in the recommendation list, known as Cold-start problem. This thesis investigates recommendation based on a novel form of content features, extracted from movies, in order to generate recommendation for users. Such features represent the visual aspects of movies, based on Deep Learning models, and hence, do not require any human annotation when extracted. The proposed technique has been evaluated in both offline and online evaluations using a large dataset of movies. The online evaluation has been carried out in a evaluation framework developed for this thesis. Results from the offline and online evaluation (N=150) show that automatically extracted visual features can mitigate the cold-start problem by generating recommendation with a superior quality compared to different baselines, including recommendation based on human-annotated features. The results also point to subtitles as a high-quality future source of automatically extracted features. The visual feature dataset, named DeepCineProp13K and the subtitle dataset, CineSub3K, as well as the proposed evaluation framework are all made openly available online in a designated Github repository. |
| Beyond Algorithmic Fairness in Recommender System Working paper Mehdi Elahi; Himan Abdollahpouri; Masoud Mansoury; Helma Torkamaan 2021. @workingpaper{cristin1957035,
title = {Beyond Algorithmic Fairness in Recommender System},
author = {Mehdi Elahi and Himan Abdollahpouri and Masoud Mansoury and Helma Torkamaan},
url = {https://app.cristin.no/results/show.jsf?id=1957035, Cristin
https://dl.acm.org/doi/abs/10.1145/3450614.3461685},
year = {2021},
date = {2021-01-01},
keywords = {Cristin},
pubstate = {published},
tppubtype = {workingpaper}
}
|
| Enhanced Movie Recommendation Incorporating Visual Features Working paper Mehdi Elahi; Farshad Bakhshandegan Moghaddam; Reza Hosseini; Mohammad Hossein Rimaz; Christoph Trattner 2021. @workingpaper{cristin1957034,
title = {Enhanced Movie Recommendation Incorporating Visual Features},
author = {Mehdi Elahi and Farshad Bakhshandegan Moghaddam and Reza Hosseini and Mohammad Hossein Rimaz and Christoph Trattner},
url = {https://app.cristin.no/results/show.jsf?id=1957034, Cristin},
year = {2021},
date = {2021-01-01},
keywords = {Cristin},
pubstate = {published},
tppubtype = {workingpaper}
}
|
| Medieundersøkelsen 2021: Har koronadekningen svekket tilliten til mediene? Presentation Erik Knudsen Nordiske Mediedager 2021, 01.01.2021. @misc{cristin1957213,
title = {Medieundersøkelsen 2021: Har koronadekningen svekket tilliten til mediene?},
author = {Erik Knudsen},
url = {https://app.cristin.no/results/show.jsf?id=1957213, Cristin
https://www.nordiskemediedager.no/medieundersoekelsen/medieundersoekelsen/},
year = {2021},
date = {2021-01-01},
howpublished = {Nordiske Mediedager 2021},
keywords = {Cristin},
pubstate = {published},
tppubtype = {presentation}
}
|
| The Effect of the COVID-19 Pandemic Crisis on Trust in the News Media: Evidence From Three Panel Waves With a Pre-Crisis Baseline Erik Knudsen Presentation Erik Knudsen; Åsta Dyrnes Nordø; Magnus Hoem Iversen 71st Annual ICA Conference, 01.01.2021. @misc{cristin1957204,
title = {The Effect of the COVID-19 Pandemic Crisis on Trust in the News Media: Evidence From Three Panel Waves With a Pre-Crisis Baseline Erik Knudsen},
author = {Erik Knudsen and Åsta Dyrnes Nordø and Magnus Hoem Iversen},
url = {https://app.cristin.no/results/show.jsf?id=1957204, Cristin},
year = {2021},
date = {2021-01-01},
howpublished = {71st Annual ICA Conference},
keywords = {Cristin},
pubstate = {published},
tppubtype = {presentation}
}
|
| The Promise and Perils of Algorithmic News Recommenders' Influence on Democracy Presentation Erik Knudsen TEDxBergen2021, 01.01.2021. @misc{cristin1957207,
title = {The Promise and Perils of Algorithmic News Recommenders' Influence on Democracy},
author = {Erik Knudsen},
url = {https://app.cristin.no/results/show.jsf?id=1957207, Cristin
https://youtu.be/B3qHJC5LwJQ},
year = {2021},
date = {2021-01-01},
howpublished = {TEDxBergen2021},
keywords = {Cristin},
pubstate = {published},
tppubtype = {presentation}
}
|
| How can news sites personalize audiences's news experiences without making audiences more polarized and fragmented? Working paper Erik Knudsen 2021. @workingpaper{cristin1957727,
title = {How can news sites personalize audiences's news experiences without making audiences more polarized and fragmented? },
author = {Erik Knudsen},
url = {https://app.cristin.no/results/show.jsf?id=1957727, Cristin},
year = {2021},
date = {2021-01-01},
keywords = {Cristin},
pubstate = {published},
tppubtype = {workingpaper}
}
|
| What can TV companies do for teenagers who are on their phone all the time? Working paper John Magnus Ragnhildson Dahl 2021. @workingpaper{cristin1957717,
title = {What can TV companies do for teenagers who are on their phone all the time?},
author = {John Magnus Ragnhildson Dahl},
url = {https://app.cristin.no/results/show.jsf?id=1957717, Cristin},
year = {2021},
date = {2021-01-01},
keywords = {Cristin},
pubstate = {published},
tppubtype = {workingpaper}
}
|
| Datafication, Media and Democracy: Transformation of news work in datafied society Working paper Ana Milojevic 2021. @workingpaper{cristin1957739,
title = {Datafication, Media and Democracy: Transformation of news work in datafied society},
author = {Ana Milojevic},
url = {https://app.cristin.no/results/show.jsf?id=1957739, Cristin},
year = {2021},
date = {2021-01-01},
keywords = {Cristin},
pubstate = {published},
tppubtype = {workingpaper}
}
|
| Why won't young people pay for news? Working paper Marianne Borchgrevink-Brækhus 2021. @workingpaper{cristin1957735,
title = {Why won't young people pay for news?},
author = {Marianne Borchgrevink-Brækhus},
url = {https://app.cristin.no/results/show.jsf?id=1957735, Cristin},
year = {2021},
date = {2021-01-01},
keywords = {Cristin},
pubstate = {published},
tppubtype = {workingpaper}
}
|
| Kva datamaskiner kan gjere Medium Lars Nyre; Bjørnar Tessem Dag og Tid, 2021. @media{cristin1957728,
title = {Kva datamaskiner kan gjere},
author = {Lars Nyre and Bjørnar Tessem},
url = {https://app.cristin.no/results/show.jsf?id=1957728, Cristin},
year = {2021},
date = {2021-01-01},
howpublished = {Dag og Tid},
keywords = {Cristin},
pubstate = {published},
tppubtype = {media}
}
|
| Fake news og mediebruk Presentation Hallvard Moe Vestlandsseminaret, 01.01.2021. @misc{cristin1957718,
title = {Fake news og mediebruk},
author = {Hallvard Moe},
url = {https://app.cristin.no/results/show.jsf?id=1957718, Cristin},
year = {2021},
date = {2021-01-01},
howpublished = {Vestlandsseminaret},
keywords = {Cristin},
pubstate = {published},
tppubtype = {presentation}
}
|
| What Matters in Professional Drone Pilots’ Practice? An Interview Study to Understand the Complexity of Their Work and Inform Human-Drone Interaction Research Proceeding Sarah Ljungblad; Yemao Man; Mehmet Aydın Baytaş; Mafalda Gamboa; Morten Fjeld; Mohammad Obaid ACM CHI on human factors in computing systems conference proceeding, 2021. @proceedings{cristin2003885,
title = {What Matters in Professional Drone Pilots’ Practice? An Interview Study to Understand the Complexity of Their Work and Inform Human-Drone Interaction Research},
author = {Sarah Ljungblad and Yemao Man and Mehmet Aydın Baytaş and Mafalda Gamboa and Morten Fjeld and Mohammad Obaid},
url = {https://app.cristin.no/results/show.jsf?id=2003885, Cristin},
year = {2021},
date = {2021-01-01},
howpublished = {ACM CHI on human factors in computing systems conference proceeding},
keywords = {Cristin},
pubstate = {published},
tppubtype = {proceedings}
}
|
| Kvifor Google-briller vart ein fiasko Medium Lars Nyre; Bjørnar Tessem Dag og Tid, 2021. @media{cristin1942262,
title = {Kvifor Google-briller vart ein fiasko},
author = {Lars Nyre and Bjørnar Tessem},
url = {https://app.cristin.no/results/show.jsf?id=1942262, Cristin},
year = {2021},
date = {2021-01-01},
howpublished = {Dag og Tid},
keywords = {Cristin},
pubstate = {published},
tppubtype = {media}
}
|
| Content Analysis and Production Presentation Bjørnar Tessem; Andreas L. Opdahl MediaFutures Annual Meeting 2021, 01.01.2021. @misc{cristin1942264,
title = {Content Analysis and Production},
author = {Bjørnar Tessem and Andreas L. Opdahl},
url = {https://app.cristin.no/results/show.jsf?id=1942264, Cristin},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
howpublished = {MediaFutures Annual Meeting 2021},
keywords = {Cristin},
pubstate = {published},
tppubtype = {presentation}
}
|
| Changing Salty Food Preferences with Visual and TextualExplanations in a Search Interface Journal Article Arngeir Berge; Vegard Velle Sjøen; Alain D. Starke; Christoph Trattner In: CEUR Workshop Proceedings, 2021. @article{cristin1933059,
title = {Changing Salty Food Preferences with Visual and TextualExplanations in a Search Interface},
author = {Arngeir Berge and Vegard Velle Sjøen and Alain D. Starke and Christoph Trattner},
url = {https://app.cristin.no/results/show.jsf?id=1933059, Cristin
http://ceur-ws.org/Vol-2903/IUI21WS-HEALTHI-2.pdf},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CEUR Workshop Proceedings},
abstract = {Salt is consumed at too high levels in the general population, causing high blood pressure and related health problems. In this paper, we present results of ongoing research that tries to reduce salt intake via technology and in particular from an interface perspective. In detail, this paper features results of a study that examines the extent to which visual and textual explanations in a search interface can change salty food preferences. An online user study with 200 participants demonstrates that this is possible in food search results by accompanying recipes with a visual taste map that includes salt-replacer herbs and spices in the calculation of salty taste.},
keywords = {Cristin},
pubstate = {published},
tppubtype = {article}
}
Salt is consumed at too high levels in the general population, causing high blood pressure and related health problems. In this paper, we present results of ongoing research that tries to reduce salt intake via technology and in particular from an interface perspective. In detail, this paper features results of a study that examines the extent to which visual and textual explanations in a search interface can change salty food preferences. An online user study with 200 participants demonstrates that this is possible in food search results by accompanying recipes with a visual taste map that includes salt-replacer herbs and spices in the calculation of salty taste. |
| Contagious "Corona" Compounding by Journalists in a CLARIN Newspaper Monitor Corpus Inproceedings Koenraad De Smedt In: 2021. @inproceedings{cristin1918658,
title = {Contagious "Corona" Compounding by Journalists in a CLARIN Newspaper Monitor Corpus},
author = {Koenraad De Smedt},
url = {https://app.cristin.no/results/show.jsf?id=1918658, Cristin
https://ecp.ep.liu.se/index.php/clarin/article/view/10/209},
doi = {https://doi.org/https://doi.org/10.3384/ecp18010},
year = {2021},
date = {2021-01-01},
keywords = {Cristin},
pubstate = {published},
tppubtype = {inproceedings}
}
|
| How the public understands news media trust: An open-ended approach Journal Article Erik Knudsen; Stefan Dahlberg; Magnus Hoem Iversen; Mikael Poul Johannesson; Silje Nygaard In: Journalism - Theory, Practice & Criticism, 2021. @article{cristin1902285,
title = {How the public understands news media trust: An open-ended approach},
author = {Erik Knudsen and Stefan Dahlberg and Magnus Hoem Iversen and Mikael Poul Johannesson and Silje Nygaard},
url = {https://app.cristin.no/results/show.jsf?id=1902285, Cristin},
doi = {https://doi.org/10.1177/14648849211005892},
year = {2021},
date = {2021-01-01},
journal = {Journalism - Theory, Practice & Criticism},
keywords = {Cristin},
pubstate = {published},
tppubtype = {article}
}
|
| Developing a Software Reference Architecture for Journalistic Knowledge Platforms Journal Article Marc Gallofré Ocaña; Andreas L. Opdahl In: CEUR Workshop Proceedings, 2021. @article{cristin1949655,
title = {Developing a Software Reference Architecture for Journalistic Knowledge Platforms},
author = {Marc Gallofré Ocaña and Andreas L. Opdahl},
url = {https://app.cristin.no/results/show.jsf?id=1949655, Cristin
http://ceur-ws.org/Vol-2978/saml-paper2.pdf},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CEUR Workshop Proceedings},
keywords = {Cristin},
pubstate = {published},
tppubtype = {article}
}
|
| Predicting Feature-based Similarity in the News Domain Using Human Judgments Inproceedings Alain D. Starke; Sebastian Øverhaug Larsen; Christoph Trattner In: Association for Computing Machinery (ACM), 2021. @inproceedings{cristin1956594,
title = {Predicting Feature-based Similarity in the News Domain Using Human Judgments},
author = {Alain D. Starke and Sebastian Øverhaug Larsen and Christoph Trattner},
url = {https://app.cristin.no/results/show.jsf?id=1956594, Cristin},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Association for Computing Machinery (ACM)},
keywords = {Cristin},
pubstate = {published},
tppubtype = {inproceedings}
}
|
| Investigating the impact of recommender systems on user-based and item-based popularity bias Journal Article Mehdi Elahi; Danial Khosh Kholgh; Mohammad Sina Kiarostami; Sorush Saghari; Shiva Parsa Rad; Marko Tkalcic In: Information Processing & Management, 2021. @article{cristin1953363,
title = {Investigating the impact of recommender systems on user-based and item-based popularity bias},
author = {Mehdi Elahi and Danial Khosh Kholgh and Mohammad Sina Kiarostami and Sorush Saghari and Shiva Parsa Rad and Marko Tkalcic},
url = {https://app.cristin.no/results/show.jsf?id=1953363, Cristin
https://www.sciencedirect.com/science/article/pii/S0306457321001436},
doi = {https://doi.org/10.1016/j.ipm.2021.102655},
year = {2021},
date = {2021-01-01},
journal = {Information Processing & Management},
abstract = {Recommender Systems are decision support tools that adopt advanced algorithms in order to help users to find less-explored items that can be interesting for them. While recommender systems may offer a range of attractive benefits, they may also intensify undesired effects, such as the Popularity Bias, where a few popular users/items get more popular and many unpopular users/items get more unpopular.
In this paper, we study the impact of different recommender algorithms on the popularity bias in different application domains and recommendation scenarios. We have designed a comprehensive evaluation methodology by considering two different recommendation scenarios, i.e., the user-based scenario (e.g., recommending users to users to follow), and the item-based scenario (e.g., recommending items to users to consume). We have used two large datasets, Twitter and Movielens, and compared a wide range of classical and modern recommender algorithms by considering a diverse range of metrics, such as PR-AUC, RCE, Gini index, and Entropy Score.
The results have shown a substantial difference between different scenarios and different recommendation domains. According to our observations, while the recommendation of users to users may increase the popularity bias in the system, the recommendation of items to users may indeed decrease it. Moreover, while we have measured a different level of popularity bias in different languages (i.e., English, Spanish, Portuguese, and Japaneses), the above-noted phenomena has been consistently observed in all of these languages.},
keywords = {Cristin},
pubstate = {published},
tppubtype = {article}
}
Recommender Systems are decision support tools that adopt advanced algorithms in order to help users to find less-explored items that can be interesting for them. While recommender systems may offer a range of attractive benefits, they may also intensify undesired effects, such as the Popularity Bias, where a few popular users/items get more popular and many unpopular users/items get more unpopular.
In this paper, we study the impact of different recommender algorithms on the popularity bias in different application domains and recommendation scenarios. We have designed a comprehensive evaluation methodology by considering two different recommendation scenarios, i.e., the user-based scenario (e.g., recommending users to users to follow), and the item-based scenario (e.g., recommending items to users to consume). We have used two large datasets, Twitter and Movielens, and compared a wide range of classical and modern recommender algorithms by considering a diverse range of metrics, such as PR-AUC, RCE, Gini index, and Entropy Score.
The results have shown a substantial difference between different scenarios and different recommendation domains. According to our observations, while the recommendation of users to users may increase the popularity bias in the system, the recommendation of items to users may indeed decrease it. Moreover, while we have measured a different level of popularity bias in different languages (i.e., English, Spanish, Portuguese, and Japaneses), the above-noted phenomena has been consistently observed in all of these languages. |
| Promoting Healthy Food Choices Online: A Case for Multi-List Recommender Systems Inproceedings Alain D. Starke; Christoph Trattner In: Association for Computing Machinery (ACM), 2021. @inproceedings{cristin1956555,
title = {Promoting Healthy Food Choices Online: A Case for Multi-List Recommender Systems},
author = {Alain D. Starke and Christoph Trattner},
url = {https://app.cristin.no/results/show.jsf?id=1956555, Cristin},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Association for Computing Machinery (ACM)},
keywords = {Cristin},
pubstate = {published},
tppubtype = {inproceedings}
}
|
| The Cholesterol Factor: Balancing Accuracy and Health in Recipe Recommendation Through a Nutrient-Specific Metric Inproceedings Alain D. Starke; Christoph Trattner; Hedda Bakken; Martin Skivenesvåg Johannessen; Vegard Solberg In: Association for Computing Machinery (ACM), 2021. @inproceedings{cristin1956600,
title = {The Cholesterol Factor: Balancing Accuracy and Health in Recipe Recommendation Through a Nutrient-Specific Metric},
author = {Alain D. Starke and Christoph Trattner and Hedda Bakken and Martin Skivenesvåg Johannessen and Vegard Solberg},
url = {https://app.cristin.no/results/show.jsf?id=1956600, Cristin},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Association for Computing Machinery (ACM)},
keywords = {Cristin},
pubstate = {published},
tppubtype = {inproceedings}
}
|
| Recommending Videos in Cold Start With Automatic Visual Tags Inproceedings Mehdi Elahi; Farshad Bakhshandegan Moghaddam; Reza Hosseini; Mohammad Hossein Rimaz; Nabil El Ioini; Marko Tkalcic; Christoph Trattner; Tammam Tillo In: Association for Computing Machinery (ACM), 2021. @inproceedings{cristin1956967,
title = {Recommending Videos in Cold Start With Automatic Visual Tags},
author = {Mehdi Elahi and Farshad Bakhshandegan Moghaddam and Reza Hosseini and Mohammad Hossein Rimaz and Nabil El Ioini and Marko Tkalcic and Christoph Trattner and Tammam Tillo},
url = {https://app.cristin.no/results/show.jsf?id=1956967, Cristin
https://dl.acm.org/doi/10.1145/3450614.3461687},
year = {2021},
date = {2021-01-01},
booktitle = {Association for Computing Machinery (ACM)},
abstract = {This paper addresses the so-called New Item problem in video Recommender Systems, as part of Cold Start. New item problem occurs when a new item is added to the system catalog, and the recommender system has no or little data describing that item. This could cause the system to fail to meaningfully recommend the new item to the users. We propose a novel technique that can generate cold start recommendation by utilizing automatic visual tags, i.e., tags that are automatically annotated by deeply analyzing the content of the videos and detecting faces, objects, and even celebrities within the videos. The automatic visual tags do not need any human involvement and have been shown to be very effective in representing the video content. In order to evaluate our proposed technique, we have performed a set of experiments using a large dataset of videos. The results have shown that the automatically extracted visual tags can be incorporated into the cold start recommendation process and achieve superior results compared to the recommendation based on human-annotated tags.},
keywords = {Cristin},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper addresses the so-called New Item problem in video Recommender Systems, as part of Cold Start. New item problem occurs when a new item is added to the system catalog, and the recommender system has no or little data describing that item. This could cause the system to fail to meaningfully recommend the new item to the users. We propose a novel technique that can generate cold start recommendation by utilizing automatic visual tags, i.e., tags that are automatically annotated by deeply analyzing the content of the videos and detecting faces, objects, and even celebrities within the videos. The automatic visual tags do not need any human involvement and have been shown to be very effective in representing the video content. In order to evaluate our proposed technique, we have performed a set of experiments using a large dataset of videos. The results have shown that the automatically extracted visual tags can be incorporated into the cold start recommendation process and achieve superior results compared to the recommendation based on human-annotated tags. |
| “Serving Each User”: Supporting Different Eating Goals Through a Multi-List Recommender Interface Inproceedings Alain D. Starke; Edis Asotic; Christoph Trattner In: Association for Computing Machinery (ACM), 2021. @inproceedings{cristin1956504,
title = {“Serving Each User”: Supporting Different Eating Goals Through a Multi-List Recommender Interface},
author = {Alain D. Starke and Edis Asotic and Christoph Trattner},
url = {https://app.cristin.no/results/show.jsf?id=1956504, Cristin},
doi = {https://doi.org/10.1145/3460231.3474232},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Association for Computing Machinery (ACM)},
keywords = {Cristin},
pubstate = {published},
tppubtype = {inproceedings}
}
|
| Exploring the effects of natural language justifications on food recommender systems Inproceedings Cataldo Musto; Alain D. Starke; Christoph Trattner; Amon Rapp; Giovanni Semeraro In: Association for Computing Machinery (ACM), 2021. @inproceedings{cristin1956541,
title = {Exploring the effects of natural language justifications on food recommender systems},
author = {Cataldo Musto and Alain D. Starke and Christoph Trattner and Amon Rapp and Giovanni Semeraro},
url = {https://app.cristin.no/results/show.jsf?id=1956541, Cristin},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Association for Computing Machinery (ACM)},
keywords = {Cristin},
pubstate = {published},
tppubtype = {inproceedings}
}
|
| Changing Salty Food Preferences with Visual and Textual Explanations in a Search Interface Inproceedings Arngeir Berge; Vegard Velle Sjøen; Alain D. Starke; Christoph Trattner In: Association for Computing Machinery (ACM), 2021. @inproceedings{cristin1956563,
title = {Changing Salty Food Preferences with Visual and Textual Explanations in a Search Interface},
author = {Arngeir Berge and Vegard Velle Sjøen and Alain D. Starke and Christoph Trattner},
url = {https://app.cristin.no/results/show.jsf?id=1956563, Cristin},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Association for Computing Machinery (ACM)},
keywords = {Cristin},
pubstate = {published},
tppubtype = {inproceedings}
}
|
| MORS 2021: 1st Workshop on Multi Objective Recommender Systems Inproceedings Himan Abdollahpouri; Mehdi Elahi; Masoud Mansoury; Shaghayegh Sahebi; Zahra Nazari; Allison Chaney; Babak Loni In: Association for Computing Machinery (ACM), 2021. @inproceedings{cristin1956978,
title = {MORS 2021: 1st Workshop on Multi Objective Recommender Systems},
author = {Himan Abdollahpouri and Mehdi Elahi and Masoud Mansoury and Shaghayegh Sahebi and Zahra Nazari and Allison Chaney and Babak Loni},
url = {https://app.cristin.no/results/show.jsf?id=1956978, Cristin
https://dl.acm.org/doi/10.1145/3460231.3470936},
year = {2021},
date = {2021-01-01},
booktitle = {Association for Computing Machinery (ACM)},
abstract = {Historically, the main criterion for a successful recommender system was the relevance of the recommended items to the user. In other words, the only objective for the recommendation algorithm was to learn user’s preferences for different items and generate recommendations accordingly. However, real-world recommender systems are well beyond a simple objective and often need to take into account multiple objectives simultaneously. These objectives can be either from the users’ perspective or they could come from other stakeholders such as item providers or any party that could be impacted by the recommendations. Such multi-objective and multi-stakeholder recommenders present unique challenges and these challenges were the focus of the MORS workshop.},
keywords = {Cristin},
pubstate = {published},
tppubtype = {inproceedings}
}
Historically, the main criterion for a successful recommender system was the relevance of the recommended items to the user. In other words, the only objective for the recommendation algorithm was to learn user’s preferences for different items and generate recommendations accordingly. However, real-world recommender systems are well beyond a simple objective and often need to take into account multiple objectives simultaneously. These objectives can be either from the users’ perspective or they could come from other stakeholders such as item providers or any party that could be impacted by the recommendations. Such multi-objective and multi-stakeholder recommenders present unique challenges and these challenges were the focus of the MORS workshop. |
2020
|
Folk theories of algorithms: Understanding digital irritation Journal Article Brita Ytre-Arne; Hallvard Moe In: Media, Culture & Society, 2020, (Pre SFI). @article{Arne2020,
title = {Folk theories of algorithms: Understanding digital irritation},
author = {Brita Ytre-Arne and Hallvard Moe},
year = {2020},
date = {2020-12-31},
journal = {Media, Culture & Society},
series = {TEST},
note = {Pre SFI},
keywords = {WP1: Understanding Media Experiences},
pubstate = {published},
tppubtype = {article}
}
|
| A knowledge-graph platform for newsrooms Journal Article Arne Berven; Ole A. Christensen; Sindre Moldeklev; Andreas L. Opdahl; Kjetil A. Villanger In: Computers in Industry, vol. 123, no. 103321, 2020, (Pre SFI). @article{Berven2020,
title = {A knowledge-graph platform for newsrooms},
author = {Arne Berven and Ole A. Christensen and Sindre Moldeklev and Andreas L. Opdahl and Kjetil A. Villanger },
url = {https://reader.elsevier.com/reader/sd/pii/S0166361520305558?token=F8A21A513C97BFF598C2755575B3C89174B3D404E2EDDD23EC37966A2754ACA1700011EBBCF52ADE2845ADBC12D40041},
doi = {https://doi.org/10.1016/j.compind.2020.103321},
year = {2020},
date = {2020-12-01},
urldate = {2020-12-01},
journal = {Computers in Industry},
volume = {123},
number = {103321},
abstract = {Journalism is challenged by digitalisation and social media, resulting in lower subscription numbers and reduced advertising income. Information and communication techniques (ICT) offer new opportunities. Our research group is collaborating with a software developer of news production tools for the international market to explore how social, open, and other data sources can be leveraged for journalistic purposes. We have developed an architecture and prototype called News Hunter that uses knowledge graphs, natural-language processing (NLP), and machine learning (ML) together to support journalists. Our focus is on combining existing data sources and computation and storage techniques into a flexible architecture for news journalism. The paper presents News Hunter along with plans and possibilities for future work.},
note = {Pre SFI},
keywords = {Computational journalism, Journalistic knowledge platforms, Knowledge graphs, Machine learning (ML), Natural-language processing (NLP), Newsroom systems, Ontology, OWL, RDF, Semantic technologies, WP3: Media Content Production and Analysis},
pubstate = {published},
tppubtype = {article}
}
Journalism is challenged by digitalisation and social media, resulting in lower subscription numbers and reduced advertising income. Information and communication techniques (ICT) offer new opportunities. Our research group is collaborating with a software developer of news production tools for the international market to explore how social, open, and other data sources can be leveraged for journalistic purposes. We have developed an architecture and prototype called News Hunter that uses knowledge graphs, natural-language processing (NLP), and machine learning (ML) together to support journalists. Our focus is on combining existing data sources and computation and storage techniques into a flexible architecture for news journalism. The paper presents News Hunter along with plans and possibilities for future work. |
| Experiments in Lifelog Organisation and Retrieval at NTCIR Book Chapter Cathal Gurrin; Hideo Joho; Frank Hopfgartner; Liting Zhou; Rami Albatal; Graham Healy; Duc-Tien Dang-Nguyen In: Evaluating Information Retrieval and Access Tasks, Chapter 13, pp. 187-203, Springer, Singapore, 2020, (Pre SFI). @inbook{Gurrin2020,
title = {Experiments in Lifelog Organisation and Retrieval at NTCIR},
author = {Cathal Gurrin and Hideo Joho and Frank Hopfgartner and Liting Zhou and Rami Albatal and Graham Healy and Duc-Tien Dang-Nguyen},
url = {https://www.researchgate.net/publication/344047066_Experiments_in_Lifelog_Organisation_and_Retrieval_at_NTCIR},
doi = {10.1007/978-981-15-5554-1_13},
year = {2020},
date = {2020-12-01},
urldate = {2020-12-01},
booktitle = {Evaluating Information Retrieval and Access Tasks},
pages = {187-203},
publisher = {Springer},
address = {Singapore},
chapter = {13},
abstract = {Lifelogging can be described as the process by which individuals use various software and hardware devices to gather large archives of multimodal personal data from multiple sources and store them in a personal data archive, called a lifelog. The Lifelog task at NTCIR was a comparative benchmarking exercise with the aim of encouraging research into the organisation and retrieval of data from multimodal lifelogs. The Lifelog task ran for over 4 years from NTCIR-12 until NTCIR-14 (2015.02–2019.06); it supported participants to submit to five subtasks, each tackling a different challenge related to lifelog retrieval. In this chapter, a motivation is given for the Lifelog task and a review of progress since NTCIR-12 is presented. Finally, the lessons learned and challenges within the domain of lifelog retrieval are presented.},
note = {Pre SFI},
keywords = {WP3: Media Content Production and Analysis},
pubstate = {published},
tppubtype = {inbook}
}
Lifelogging can be described as the process by which individuals use various software and hardware devices to gather large archives of multimodal personal data from multiple sources and store them in a personal data archive, called a lifelog. The Lifelog task at NTCIR was a comparative benchmarking exercise with the aim of encouraging research into the organisation and retrieval of data from multimodal lifelogs. The Lifelog task ran for over 4 years from NTCIR-12 until NTCIR-14 (2015.02–2019.06); it supported participants to submit to five subtasks, each tackling a different challenge related to lifelog retrieval. In this chapter, a motivation is given for the Lifelog task and a review of progress since NTCIR-12 is presented. Finally, the lessons learned and challenges within the domain of lifelog retrieval are presented. |
| Gender and sentiment, critics and authors: a dataset of Norwegian book reviews Journal Article Samia Touileb; Lilja Øvrelid; Erik Velldal In: Gender Bias in Natural Language Processing. Association for Computational Linguistics, 2020, (Pre SFI). @article{Touileb2020,
title = {Gender and sentiment, critics and authors: a dataset of Norwegian book reviews},
author = {Samia Touileb and Lilja Øvrelid and Erik Velldal},
url = {https://www.aclweb.org/anthology/2020.gebnlp-1.11.pdf},
year = {2020},
date = {2020-12-01},
journal = {Gender Bias in Natural Language Processing. Association for Computational Linguistics},
abstract = {Gender bias in models and datasets is widely studied in NLP. The focus has usually been on analysing how females and males express themselves, or how females and males are described. However, a less studied aspect is the combination of these two perspectives, how female and male describe the same or opposite gender. In this paper, we present a new gender annotated sentiment dataset of critics reviewing the works of female and male authors. We investigate if this newly annotated dataset contains differences in how the works of male and female authors are critiqued, in particular in terms of positive and negative sentiment. We also explore the differences in how this is done by male and female critics. We show that there are differences in how critics assess the works of authors of the same or opposite gender. For example, male critics rate crime novels written by females, and romantic and sentimental works written by males, more negatively.},
note = {Pre SFI},
keywords = {WP5: Norwegian Language Technologies},
pubstate = {published},
tppubtype = {article}
}
Gender bias in models and datasets is widely studied in NLP. The focus has usually been on analysing how females and males express themselves, or how females and males are described. However, a less studied aspect is the combination of these two perspectives, how female and male describe the same or opposite gender. In this paper, we present a new gender annotated sentiment dataset of critics reviewing the works of female and male authors. We investigate if this newly annotated dataset contains differences in how the works of male and female authors are critiqued, in particular in terms of positive and negative sentiment. We also explore the differences in how this is done by male and female critics. We show that there are differences in how critics assess the works of authors of the same or opposite gender. For example, male critics rate crime novels written by females, and romantic and sentimental works written by males, more negatively. |
| Improving sentiment analysis with multi-task learning of negation Journal Article J Barnes; Erik Velldal; Lilja Øvrelid In: 2020, (Pre SFI). @article{Barnes2020,
title = {Improving sentiment analysis with multi-task learning of negation},
author = {J Barnes and Erik Velldal and Lilja Øvrelid},
url = {https://www.cambridge.org/core/journals/natural-language-engineering/article/abs/improving-sentiment-analysis-with-multitask-learning-of-negation/14EF2B829EC4B8EC29E7C0C5C77B95B0},
year = {2020},
date = {2020-11-11},
note = {Pre SFI},
keywords = {WP5: Norwegian Language Technologies},
pubstate = {published},
tppubtype = {article}
}
|
| Changing news use. Unchanged news experiences? Book Irene Costera Meijer; Tim Groot Kormelink Routledge, 2020, ISBN: 9780367485788, (Pre SFI). @book{Meijer2020c,
title = {Changing news use. Unchanged news experiences?},
author = {Irene Costera Meijer and Tim Groot Kormelink},
url = {https://www.routledge.com/Changing-News-Use-Unchanged-News-Experiences/Meijer-Kormelink/p/book/9780367485788},
isbn = {9780367485788},
year = {2020},
date = {2020-11-09},
publisher = {Routledge},
abstract = {Changing News Use pulls from empirical research to introduce and describe
how changing news user patterns and journalism practices have been
mutually disruptive, exploring what journalists and the news media can
learn from these changes.
Based on 15 years of audience research, the authors provide an in-depth
description of what people do with news and how this has diversified
over time, from reading, watching, and listening to a broader spectrum
of user practices including checking, scrolling, tagging, and avoiding.
By emphasizing people’s own experience of journalism, this book also
investigates what two prominent audience measurements – clicking and
spending time – mean from a user perspective. The book outlines ways to
overcome the dilemma of providing what people apparently want (attentiongrabbing
news features) and delivering what people apparently need (what
journalists see as important information), suggesting alternative ways to
investigate and become sensitive to the practices, preferences, and pleasures
of audiences and discussing what these research findings might mean for
everyday journalism practice.
The book is a valuable and timely resource for academics and researchers
interested in the fields of journalism studies, sociology, digital media, and
communication.},
note = {Pre SFI},
keywords = {WP1: Understanding Media Experiences},
pubstate = {published},
tppubtype = {book}
}
Changing News Use pulls from empirical research to introduce and describe
how changing news user patterns and journalism practices have been
mutually disruptive, exploring what journalists and the news media can
learn from these changes.
Based on 15 years of audience research, the authors provide an in-depth
description of what people do with news and how this has diversified
over time, from reading, watching, and listening to a broader spectrum
of user practices including checking, scrolling, tagging, and avoiding.
By emphasizing people’s own experience of journalism, this book also
investigates what two prominent audience measurements – clicking and
spending time – mean from a user perspective. The book outlines ways to
overcome the dilemma of providing what people apparently want (attentiongrabbing
news features) and delivering what people apparently need (what
journalists see as important information), suggesting alternative ways to
investigate and become sensitive to the practices, preferences, and pleasures
of audiences and discussing what these research findings might mean for
everyday journalism practice.
The book is a valuable and timely resource for academics and researchers
interested in the fields of journalism studies, sociology, digital media, and
communication. |
| The complexity landscape of outcome determination in judgment aggregation Journal Article Ulle Endriss; Ronald de Haan; Jerôme Lang; Marija Slavkovik In: Journal of Artificial Intelligence Research, vol. 69, pp. 687–731, 2020, (Pre SFI). @article{Endriss2020,
title = {The complexity landscape of outcome determination in judgment aggregation},
author = {Ulle Endriss and Ronald de Haan and Jerôme Lang and Marija Slavkovik },
url = {https://www.jair.org/index.php/jair/article/view/11970/26619},
doi = {10.1613/jair.1.11970},
year = {2020},
date = {2020-11-04},
journal = {Journal of Artificial Intelligence Research},
volume = {69},
pages = {687–731},
abstract = {We provide a comprehensive analysis of the computational complexity of the outcome determinationproblem for the most important aggregation rules proposed in the literature on logic-based judgmentaggregation. Judgment aggregation is a powerful and flexible framework for studying problems ofcollective decision making that has attracted interest in a range of disciplines, including Legal Theory,Philosophy, Economics, Political Science, and Artificial Intelligence. The problem of computing theoutcome for a given list of individual judgments to be aggregated into a single collective judgment isthe most fundamental algorithmic challenge arising in this context. Our analysis applies to severaldifferent variants of the basic framework of judgment aggregation that have been discussed in theliterature, as well as to a new framework that encompasses all existing such frameworks in terms ofexpressive power and representational succinctness.},
note = {Pre SFI},
keywords = {WP2: User Modeling Personalization and Engagement},
pubstate = {published},
tppubtype = {article}
}
We provide a comprehensive analysis of the computational complexity of the outcome determinationproblem for the most important aggregation rules proposed in the literature on logic-based judgmentaggregation. Judgment aggregation is a powerful and flexible framework for studying problems ofcollective decision making that has attracted interest in a range of disciplines, including Legal Theory,Philosophy, Economics, Political Science, and Artificial Intelligence. The problem of computing theoutcome for a given list of individual judgments to be aggregated into a single collective judgment isthe most fundamental algorithmic challenge arising in this context. Our analysis applies to severaldifferent variants of the basic framework of judgment aggregation that have been discussed in theliterature, as well as to a new framework that encompasses all existing such frameworks in terms ofexpressive power and representational succinctness. |
| AI-KG: an automatically generated knowledge graph of artificial intelligence Conference Danilo Dessì; Francesco Osborne; Diego Reforgiato Recupero; Davide Buscaldi; Enrico Motta; Harald Sack nternational Semantic Web Conference, Springer, 2020, (Pre SFI). @conference{Dessì2020,
title = {AI-KG: an automatically generated knowledge graph of artificial intelligence},
author = {Danilo Dessì and Francesco Osborne and Diego Reforgiato Recupero and Davide Buscaldi and Enrico Motta and Harald Sack},
url = {https://www.researchgate.net/publication/344991487_AI-KG_an_Automatically_Generated_Knowledge_Graph_of_Artificial_Intelligence},
year = {2020},
date = {2020-11-01},
booktitle = {nternational Semantic Web Conference},
pages = {127-143},
publisher = {Springer},
abstract = {Scientific knowledge has been traditionally disseminated and preserved through research articles published in journals, conference proceedings , and online archives. However, this article-centric paradigm has been often criticized for not allowing to automatically process, categorize , and reason on this knowledge. An alternative vision is to generate a semantically rich and interlinked description of the content of research publications. In this paper, we present the Artificial Intelligence Knowledge Graph (AI-KG), a large-scale automatically generated knowledge graph that describes 820K research entities. AI-KG includes about 14M RDF triples and 1.2M reified statements extracted from 333K research publications in the field of AI, and describes 5 types of entities (tasks, methods, metrics, materials, others) linked by 27 relations. AI-KG has been designed to support a variety of intelligent services for analyzing and making sense of research dynamics, supporting researchers in their daily job, and helping to inform decision-making in funding bodies and research policymakers. AI-KG has been generated by applying an automatic pipeline that extracts entities and relationships using three tools: DyGIE++, Stanford CoreNLP, and the CSO Classifier. It then integrates and filters the resulting triples using a combination of deep learning and semantic technologies in order to produce a high-quality knowledge graph. This pipeline was evaluated on a manually crafted gold standard, yielding competitive results. AI-KG is available under CC BY 4.0 and can be downloaded as a dump or queried via a SPARQL endpoint.},
note = {Pre SFI},
keywords = {WP3: Media Content Production and Analysis},
pubstate = {published},
tppubtype = {conference}
}
Scientific knowledge has been traditionally disseminated and preserved through research articles published in journals, conference proceedings , and online archives. However, this article-centric paradigm has been often criticized for not allowing to automatically process, categorize , and reason on this knowledge. An alternative vision is to generate a semantically rich and interlinked description of the content of research publications. In this paper, we present the Artificial Intelligence Knowledge Graph (AI-KG), a large-scale automatically generated knowledge graph that describes 820K research entities. AI-KG includes about 14M RDF triples and 1.2M reified statements extracted from 333K research publications in the field of AI, and describes 5 types of entities (tasks, methods, metrics, materials, others) linked by 27 relations. AI-KG has been designed to support a variety of intelligent services for analyzing and making sense of research dynamics, supporting researchers in their daily job, and helping to inform decision-making in funding bodies and research policymakers. AI-KG has been generated by applying an automatic pipeline that extracts entities and relationships using three tools: DyGIE++, Stanford CoreNLP, and the CSO Classifier. It then integrates and filters the resulting triples using a combination of deep learning and semantic technologies in order to produce a high-quality knowledge graph. This pipeline was evaluated on a manually crafted gold standard, yielding competitive results. AI-KG is available under CC BY 4.0 and can be downloaded as a dump or queried via a SPARQL endpoint. |
