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.
2020 |
| Towards a Framework for Visual Intelligence in Service Robotics: Epistemic Requirements and Gap Analysis Journal Article Agnese Chiatti; Enrico Motta; Enrico Daga Proceedings of the 17th International Conference on Principles of Knowledge Representation and Reasoning (KR 2020), pp. 905–916, 2020, (Pre SFI). Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links: @article{Chiatti2020, title = {Towards a Framework for Visual Intelligence in Service Robotics: Epistemic Requirements and Gap Analysis}, author = {Agnese Chiatti and Enrico Motta and Enrico Daga}, url = {https://arxiv.org/ftp/arxiv/papers/2003/2003.06171.pdf}, year = {2020}, date = {2020-03-13}, journal = {Proceedings of the 17th International Conference on Principles of Knowledge Representation and Reasoning (KR 2020)}, pages = {905–916}, abstract = {A key capability required by service robots operating in real-world, dynamic environments is that of Visual Intelligence, i.e., the ability to use their vision system, reasoning components and background knowledge to make sense of their environment. In this paper, we analyze the epistemic requirements for Visual Intelligence, both in a top-down fashion, using existing frameworks for human-like Visual Intelligence in the literature, and from the bottom up, based on the errors emerging from object recognition trials in a real-world robotic scenario. Finally, we use these requirements to evaluate current knowledge bases for Service Robotics and to identify gaps in the support they provide for Visual Intelligence. These gaps provide the basis of a research agenda for developing more effective knowledge representations for Visual Intelligence.}, note = {Pre SFI}, keywords = {WP3: Media Content Production and Analysis}, pubstate = {published}, tppubtype = {article} } A key capability required by service robots operating in real-world, dynamic environments is that of Visual Intelligence, i.e., the ability to use their vision system, reasoning components and background knowledge to make sense of their environment. In this paper, we analyze the epistemic requirements for Visual Intelligence, both in a top-down fashion, using existing frameworks for human-like Visual Intelligence in the literature, and from the bottom up, based on the errors emerging from object recognition trials in a real-world robotic scenario. Finally, we use these requirements to evaluate current knowledge bases for Service Robotics and to identify gaps in the support they provide for Visual Intelligence. These gaps provide the basis of a research agenda for developing more effective knowledge representations for Visual Intelligence. |
| Named entity extraction for knowledge graphs: A literature overview Journal Article Tareq Al-Moslmi; Marc Gallofré Ocaña; Andreas Lothe Opdahl; Csaba Veres IEEE Access, 8 , pp. 32862-32881, 2020, (Pre SFI). Abstract | BibTeX | Tags: Knowledge graphs, Named-entity disambiguation, Named-entity extraction, Named-entity linking, Named-entity recognition, Natural-language processing, WP3: Media Content Production and Analysis | Links: @article{Al-Moslmi2020, title = {Named entity extraction for knowledge graphs: A literature overview}, author = {Tareq Al-Moslmi and Marc Gallofré Ocaña and Andreas Lothe Opdahl and Csaba Veres }, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8999622}, doi = {10.1109/ACCESS.2020.2973928}, year = {2020}, date = {2020-02-14}, journal = {IEEE Access}, volume = {8}, pages = {32862-32881}, abstract = {An enormous amount of digital information is expressed as natural-language (NL) text that is not easily processable by computers. Knowledge Graphs (KG) offer a widely used format for representing information in computer-processable form. Natural Language Processing (NLP) is therefore needed for mining (or lifting) knowledge graphs from NL texts. A central part of the problem is to extract the named entities in the text. The paper presents an overview of recent advances in this area, covering: Named Entity Recognition (NER), Named Entity Disambiguation (NED), and Named Entity Linking (NEL). We comment that many approaches to NED and NEL are based on older approaches to NER and need to leverage the outputs of state-of-the-art NER systems. There is also a need for standard methods to evaluate and compare named-entity extraction approaches. We observe that NEL has recently moved from being stepwise and isolated into an integrated process along two dimensions: the first is that previously sequential steps are now being integrated into end-to-end processes, and the second is that entities that were previously analysed in isolation are now being lifted in each other's context. The current culmination of these trends are the deep-learning approaches that have recently reported promising results.}, note = {Pre SFI}, keywords = {Knowledge graphs, Named-entity disambiguation, Named-entity extraction, Named-entity linking, Named-entity recognition, Natural-language processing, WP3: Media Content Production and Analysis}, pubstate = {published}, tppubtype = {article} } An enormous amount of digital information is expressed as natural-language (NL) text that is not easily processable by computers. Knowledge Graphs (KG) offer a widely used format for representing information in computer-processable form. Natural Language Processing (NLP) is therefore needed for mining (or lifting) knowledge graphs from NL texts. A central part of the problem is to extract the named entities in the text. The paper presents an overview of recent advances in this area, covering: Named Entity Recognition (NER), Named Entity Disambiguation (NED), and Named Entity Linking (NEL). We comment that many approaches to NED and NEL are based on older approaches to NER and need to leverage the outputs of state-of-the-art NER systems. There is also a need for standard methods to evaluate and compare named-entity extraction approaches. We observe that NEL has recently moved from being stepwise and isolated into an integrated process along two dimensions: the first is that previously sequential steps are now being integrated into end-to-end processes, and the second is that entities that were previously analysed in isolation are now being lifted in each other's context. The current culmination of these trends are the deep-learning approaches that have recently reported promising results. |
| Web Table Extraction, Retrieval, and Augmentation: A Survey Journal Article Shuo Zhang; Krisztian Balog ACM Transactions on Intelligent Systems and Technology (TIST), 11 (2), pp. 1-35, 2020, (Pre SFI). Abstract | BibTeX | Tags: Table augmentation, Table extraction, Table interpretation, Table mining, Table retrieval, Table search, WP2: User Modeling Personalization and Engagement | Links: @article{Zhang2020, title = {Web Table Extraction, Retrieval, and Augmentation: A Survey}, author = {Shuo Zhang and Krisztian Balog}, url = {https://arxiv.org/pdf/2002.00207.pdf}, year = {2020}, date = {2020-02-01}, journal = {ACM Transactions on Intelligent Systems and Technology (TIST)}, volume = {11}, number = {2}, pages = {1-35}, abstract = {Tables are a powerful and popular tool for organizing and manipulating data. A vast number of tables can be found on the Web, which represents a valuable knowledge resource. The objective of this survey is to synthesize and present two decades of research on web tables. In particular, we organize existing literature into six main categories of information access tasks: table extraction, table interpretation, table search, question answering, knowledge base augmentation, and table augmentation. For each of these tasks, we identify and describe seminal approaches, present relevant resources, and point out interdependencies among the different tasks.}, note = {Pre SFI}, keywords = {Table augmentation, Table extraction, Table interpretation, Table mining, Table retrieval, Table search, WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {article} } Tables are a powerful and popular tool for organizing and manipulating data. A vast number of tables can be found on the Web, which represents a valuable knowledge resource. The objective of this survey is to synthesize and present two decades of research on web tables. In particular, we organize existing literature into six main categories of information access tasks: table extraction, table interpretation, table search, question answering, knowledge base augmentation, and table augmentation. For each of these tasks, we identify and describe seminal approaches, present relevant resources, and point out interdependencies among the different tasks. |
| Morphological filter detector for image forensics applications Journal Article G. Boato; Duc-Tien Dang Nguyen; F.G.B. De Natale IEEE Access, 8 , pp. 13549-13560, 2020, (Pre SFI). Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links: @article{Boato2020, title = {Morphological filter detector for image forensics applications}, author = {G. Boato and Duc-Tien Dang Nguyen and F.G.B. De Natale}, url = {https://www.researchgate.net/publication/338524511_Morphological_Filter_Detector_for_Image_Forensics_Applications}, doi = {10.1109/ACCESS.2020.2965745}, year = {2020}, date = {2020-01-01}, journal = {IEEE Access}, volume = {8}, pages = {13549-13560}, abstract = {Mathematical morphology provides a large set of powerful non-linear image operators, widely used for feature extraction, noise removal or image enhancement. Although morphological filters might be used to remove artifacts produced by image manipulations, both on binary and graylevel documents, little effort has been spent towards their forensic identification. In this paper we propose a non-trivial extension of a deterministic approach originally detecting erosion and dilation of binary images. The proposed approach operates on grayscale images and is robust to image compression and other typical attacks. When the image is attacked the method looses its deterministic nature and uses a properly trained SVM classifier, using the original detector as a feature extractor. Extensive tests demonstrate that the proposed method guarantees very high accuracy in filtering detection, providing 100% accuracy in discriminating the presence and the type of morphological filter in raw images of three different datasets. The achieved accuracy is also good after JPEG compression, equal or above 76.8% on all datasets for quality factors above 80. The proposed approach is also able to determine the adopted structuring element for moderate compression factors. Finally, it is robust against noise addition and it can distinguish morphological filter from other filters.}, note = {Pre SFI}, keywords = {WP3: Media Content Production and Analysis}, pubstate = {published}, tppubtype = {article} } Mathematical morphology provides a large set of powerful non-linear image operators, widely used for feature extraction, noise removal or image enhancement. Although morphological filters might be used to remove artifacts produced by image manipulations, both on binary and graylevel documents, little effort has been spent towards their forensic identification. In this paper we propose a non-trivial extension of a deterministic approach originally detecting erosion and dilation of binary images. The proposed approach operates on grayscale images and is robust to image compression and other typical attacks. When the image is attacked the method looses its deterministic nature and uses a properly trained SVM classifier, using the original detector as a feature extractor. Extensive tests demonstrate that the proposed method guarantees very high accuracy in filtering detection, providing 100% accuracy in discriminating the presence and the type of morphological filter in raw images of three different datasets. The achieved accuracy is also good after JPEG compression, equal or above 76.8% on all datasets for quality factors above 80. The proposed approach is also able to determine the adopted structuring element for moderate compression factors. Finally, it is robust against noise addition and it can distinguish morphological filter from other filters. |
| Beyond “one-size-fits-all” platforms: Applying Campbell's paradigm to test personalized energy advice in the Netherlands Journal Article Alain D. Starke; Martijn C. Willemsen; Chris C.P. Snijders 59 (January 2020), pp. 1-12, 2020. Abstract | BibTeX | Tags: Conservation advice, Energy efficiency, Rasch model, Recommender systems | Links: @article{Starke2020, title = {Beyond “one-size-fits-all” platforms: Applying Campbell's paradigm to test personalized energy advice in the Netherlands}, author = {Alain D. Starke and Martijn C. Willemsen and Chris C.P. Snijders}, url = {https://www.sciencedirect.com/science/article/pii/S2214629618302615?via%3Dihub}, doi = {10.1016/j.erss.2019.101311}, year = {2020}, date = {2020-01-01}, volume = {59}, number = {January 2020}, pages = {1-12}, abstract = {When analyzing ways in which people save energy, most researchers and policy makers conceptually differentiate between curtailment (e.g. unplugging chargers) and efficiency measures (e.g. installing PV cells). However, such a two-dimensional approach is suboptimal from both a conceptual and policy perspective, as it does not consider individual differences that determine energy-saving behavior. We propose a different, one-dimensional approach, applying Campbell's Paradigm through the Rasch model, in which both curtailment and efficiency measures are intermixed on a single scale and ordered according to their behavioral costs. By matching these behavioral costs to individual energy-saving attitudes, we investigate to what extent attitude-tailored energy-saving advice can help consumers to save energy. We present the results of two studies. The first study (N = 263) reliably calibrated a one-dimensional Rasch scale that consists of 79 energy-saving measures, suitable for advice. The second study employed this scale to investigate how users (N = 196) evaluate attitude-tailored energy-saving advice in a web-based energy recommender system. Results indicate that Rasch-based recommendations can be used to effectively tailor energy-saving advice and that such attitude-tailored advice is more adequate than a number of non-personalized approaches.}, keywords = {Conservation advice, Energy efficiency, Rasch model, Recommender systems}, pubstate = {published}, tppubtype = {article} } When analyzing ways in which people save energy, most researchers and policy makers conceptually differentiate between curtailment (e.g. unplugging chargers) and efficiency measures (e.g. installing PV cells). However, such a two-dimensional approach is suboptimal from both a conceptual and policy perspective, as it does not consider individual differences that determine energy-saving behavior. We propose a different, one-dimensional approach, applying Campbell's Paradigm through the Rasch model, in which both curtailment and efficiency measures are intermixed on a single scale and ordered according to their behavioral costs. By matching these behavioral costs to individual energy-saving attitudes, we investigate to what extent attitude-tailored energy-saving advice can help consumers to save energy. We present the results of two studies. The first study (N = 263) reliably calibrated a one-dimensional Rasch scale that consists of 79 energy-saving measures, suitable for advice. The second study employed this scale to investigate how users (N = 196) evaluate attitude-tailored energy-saving advice in a web-based energy recommender system. Results indicate that Rasch-based recommendations can be used to effectively tailor energy-saving advice and that such attitude-tailored advice is more adequate than a number of non-personalized approaches. |
2019 |
| Distributed Readiness Citizenship: A Realistic, Normative Concept for Citizens’ Public Connection. Journal Article Hallvard Moe Communication Theory, 2019, ISSN: 1050–3293, (Pre SFI). Abstract | BibTeX | Tags: Citizenship, Deliberative, Democracy, Democratic Realism, Normative Theory, Public Sphere, WP1: Understanding Media Experiences | Links: @article{Moe2019, title = {Distributed Readiness Citizenship: A Realistic, Normative Concept for Citizens’ Public Connection.}, author = {Hallvard Moe}, url = {https://bora.uib.no/bora-xmlui/bitstream/handle/1956/23098/qtz016.pdf?sequence=3&isAllowed=y}, doi = {10.1093/ct/qtz016}, issn = {1050–3293}, year = {2019}, date = {2019-12-09}, journal = {Communication Theory}, abstract = {This article argues that our view of citizens as miserably failing to maintain their role in democracy is problematic, and that the problems stem from the “informed citizen” ideal: it is too demanding, but also misses the target. The article proposes an alternative normative concept for citizens’ public connection: distributed readiness citizenship. The concept highlights how the state of being prepared to act is more important than levels of measurable political knowledge. Readiness is crucial to finding enough information and relevant cues, and it cannot be assessed based on individual citizens in isolation, but should be considered as distributed, and embodied in citizens’ social networks, with a division of labor. With such a conceptualization, we are better equipped to evaluate existing conditions, judge the impact of populism and propaganda, and figure out how to improve the chances for those less well-off to participate in democracy.}, note = {Pre SFI}, keywords = {Citizenship, Deliberative, Democracy, Democratic Realism, Normative Theory, Public Sphere, WP1: Understanding Media Experiences}, pubstate = {published}, tppubtype = {article} } This article argues that our view of citizens as miserably failing to maintain their role in democracy is problematic, and that the problems stem from the “informed citizen” ideal: it is too demanding, but also misses the target. The article proposes an alternative normative concept for citizens’ public connection: distributed readiness citizenship. The concept highlights how the state of being prepared to act is more important than levels of measurable political knowledge. Readiness is crucial to finding enough information and relevant cues, and it cannot be assessed based on individual citizens in isolation, but should be considered as distributed, and embodied in citizens’ social networks, with a division of labor. With such a conceptualization, we are better equipped to evaluate existing conditions, judge the impact of populism and propaganda, and figure out how to improve the chances for those less well-off to participate in democracy. |
| Analogical News Angles from Text Similarity Conference Bjørnar Tessem Artificial Intelligence XXXVI, (11927), Springer International Publishing, 2019, (Pre SFI). Abstract | BibTeX | Tags: Analogical reasoning, Computational creativity, Document similarity, Journalism, WP3: Media Content Production and Analysis | Links: @conference{Tessem2019b, title = {Analogical News Angles from Text Similarity}, author = {Bjørnar Tessem}, editor = {Max Bramer and Miltos Petridis}, url = {https://bora.uib.no/bora-xmlui/bitstream/handle/1956/22473/SGAI_2019.pdf?sequence=4&isAllowed=y}, doi = {https://doi.org/10.1007/978-3-030-34885-4_35}, year = {2019}, date = {2019-11-19}, booktitle = {Artificial Intelligence XXXVI}, number = {11927}, pages = {449–455}, publisher = {Springer International Publishing}, abstract = {The paper presents an algorithm providing creativity support to journalists. It suggests analogical transfer of news angles from reports written about different events than the one the journalist is working on. The problem is formulated as a matching problem, where news reports with similar wordings from two events are matched, and unmatched reports from previous cases are selected as candidates for a news angle transfer. The approach is based on document similarity measures for matching and selection of transferable candidates. The algorithm has been tested on a small data set and show that the concept may be viable, but needs more exploration and evaluation in journalistic practice.}, note = {Pre SFI}, keywords = {Analogical reasoning, Computational creativity, Document similarity, Journalism, WP3: Media Content Production and Analysis}, pubstate = {published}, tppubtype = {conference} } The paper presents an algorithm providing creativity support to journalists. It suggests analogical transfer of news angles from reports written about different events than the one the journalist is working on. The problem is formulated as a matching problem, where news reports with similar wordings from two events are matched, and unmatched reports from previous cases are selected as candidates for a news angle transfer. The approach is based on document similarity measures for matching and selection of transferable candidates. The algorithm has been tested on a small data set and show that the concept may be viable, but needs more exploration and evaluation in journalistic practice. |
| Lexicon information in neural sentiment analysis: a multi-task learning approach Conference Jeremy Barnes; Samia Touileb; Lilja Øvrelid; Erik Velldal Linköping University Electronic Press, 2019, (Pre SFI). Abstract | BibTeX | Tags: WP5: Norwegian Language Technologies | Links: @conference{Barnes2019, title = {Lexicon information in neural sentiment analysis: a multi-task learning approach}, author = {Jeremy Barnes and Samia Touileb and Lilja Øvrelid and Erik Velldal}, url = {https://www.aclweb.org/anthology/W19-6119.pdf}, year = {2019}, date = {2019-10-01}, journal = {Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa)}, pages = {175–186}, publisher = {Linköping University Electronic Press}, abstract = {This paper explores the use of multi-task learning (MTL) for incorporating external knowledge in neural models. Specifically, we show how MTL can enable a BiLSTM sentiment classifier to incorporate information from sentiment lexicons. Our MTL set-up is shown to improve model performance (compared to a single-task set-up) on both English and Norwegian sentence-level sentiment datasets. The paper also introduces a new sentiment lexicon for Norwegian.}, note = {Pre SFI}, keywords = {WP5: Norwegian Language Technologies}, pubstate = {published}, tppubtype = {conference} } This paper explores the use of multi-task learning (MTL) for incorporating external knowledge in neural models. Specifically, we show how MTL can enable a BiLSTM sentiment classifier to incorporate information from sentiment lexicons. Our MTL set-up is shown to improve model performance (compared to a single-task set-up) on both English and Norwegian sentence-level sentiment datasets. The paper also introduces a new sentiment lexicon for Norwegian. |
| Learning to Recommend Similar Items from Human Judgements Journal Article Christoph Trattner; Dietmar Jannach User Modeling and User-Adapted Interaction Journal, pp. 1-50, 2019, (Pre SFI). Abstract | BibTeX | Tags: Content-basedrecommender systems, Similar item recommendations, Similarity measures, User studies | Links: @article{Trattner2020, title = {Learning to Recommend Similar Items from Human Judgements}, author = {Christoph Trattner and Dietmar Jannach}, url = {https://www.christophtrattner.info/pubs/UMUAI2019.pdf}, doi = {10.1007/s11257-019-09245-4}, year = {2019}, date = {2019-09-20}, journal = {User Modeling and User-Adapted Interaction Journal}, pages = {1-50}, abstract = {Similar item recommendations—a common feature of many Web sites—point users to other interesting objects given a currently inspected item. A common way of computing such recommendations is to use a similarity function, which expresses how much alike two given objects are. Such similarity functions are usually designed based on the specifics of the given application domain. In this work, we explore how such functions can be learned from human judgments of similarities between objects, using two domains of “quality and taste”—cooking recipe and movie recommendation—as guiding scenarios. In our approach, we first collect a few thousand pairwise similarity assessments with the help of crowdworkers. Using these data, we then train different machine learning models that can be used as similarity functions to compare objects. Offline analyses reveal for both application domains that models that combine different types of item characteristics are the best predictors for human-perceived similarity. To further validate the usefulness of the learned models, we conducted additional user studies. In these studies, we exposed participants to similar item recommendations using a set of models that were trained with different feature subsets. The results showed that the combined models that exhibited the best offline prediction performance led to the highest user-perceived similarity, but also to recommendations that were considered useful by the participants, thus confirming the feasibility of our approach.}, note = {Pre SFI}, keywords = {Content-basedrecommender systems, Similar item recommendations, Similarity measures, User studies}, pubstate = {published}, tppubtype = {article} } Similar item recommendations—a common feature of many Web sites—point users to other interesting objects given a currently inspected item. A common way of computing such recommendations is to use a similarity function, which expresses how much alike two given objects are. Such similarity functions are usually designed based on the specifics of the given application domain. In this work, we explore how such functions can be learned from human judgments of similarities between objects, using two domains of “quality and taste”—cooking recipe and movie recommendation—as guiding scenarios. In our approach, we first collect a few thousand pairwise similarity assessments with the help of crowdworkers. Using these data, we then train different machine learning models that can be used as similarity functions to compare objects. Offline analyses reveal for both application domains that models that combine different types of item characteristics are the best predictors for human-perceived similarity. To further validate the usefulness of the learned models, we conducted additional user studies. In these studies, we exposed participants to similar item recommendations using a set of models that were trained with different feature subsets. The results showed that the combined models that exhibited the best offline prediction performance led to the highest user-perceived similarity, but also to recommendations that were considered useful by the participants, thus confirming the feasibility of our approach. |
| Capturing themed evidence, a hybrid approach Conference Enrico Daga; Enrico Motta roceedings of the 10th International Conference on Knowledge Capture, 2019, (Pre SFI). Abstract | BibTeX | Tags: DBpedia, Hybrid method, Information extraction, Themed evidence, WP3: Media Content Production and Analysis | Links: @conference{Daga2019, title = {Capturing themed evidence, a hybrid approach}, author = {Enrico Daga and Enrico Motta}, url = {https://dl.acm.org/doi/pdf/10.1145/3360901.3364415}, year = {2019}, date = {2019-09-01}, booktitle = {roceedings of the 10th International Conference on Knowledge Capture}, pages = {93-100}, abstract = {The task of identifying pieces of evidence in texts is of fundamental importance in supporting qualitative studies in various domains, especially in the humanities. In this paper, we coin the expression themed evidence, to refer to (direct or indirect) traces of a fact or situation relevant to a theme of interest and study the problem of identifying them in texts. We devise a generic framework aimed at capturing themed evidence in texts based on a hybrid approach, combining statistical natural language processing, background knowledge, and Semantic Web technologies. The effectiveness of the method is demonstrated on a case study of a digital humanities database aimed at collecting and curating a repository of evidence of experiences of listening to music. Extensive experiments demonstrate that our hybrid approach outperforms alternative solutions. We also evidence its generality by testing it on a different use case in the digital humanities.}, note = {Pre SFI}, keywords = {DBpedia, Hybrid method, Information extraction, Themed evidence, WP3: Media Content Production and Analysis}, pubstate = {published}, tppubtype = {conference} } The task of identifying pieces of evidence in texts is of fundamental importance in supporting qualitative studies in various domains, especially in the humanities. In this paper, we coin the expression themed evidence, to refer to (direct or indirect) traces of a fact or situation relevant to a theme of interest and study the problem of identifying them in texts. We devise a generic framework aimed at capturing themed evidence in texts based on a hybrid approach, combining statistical natural language processing, background knowledge, and Semantic Web technologies. The effectiveness of the method is demonstrated on a case study of a digital humanities database aimed at collecting and curating a repository of evidence of experiences of listening to music. Extensive experiments demonstrate that our hybrid approach outperforms alternative solutions. We also evidence its generality by testing it on a different use case in the digital humanities. |
| Hierarchical attention networks to learn latent aspect embeddings for fake news detection Conference Rahul Mishra; Vinay Setty Proceedings of the 2019 acm sigir international conference on theory of information retrieval, Association for Computing Machinery, New York, 2019, (Pre SFI). Abstract | BibTeX | Tags: Fake news, Hierarchical attention, Latent aspect embeddings, WP3: Media Content Production and Analysis | Links: @conference{Mishra2019, title = {Hierarchical attention networks to learn latent aspect embeddings for fake news detection}, author = {Rahul Mishra and Vinay Setty}, url = {https://dl.acm.org/doi/pdf/10.1145/3341981.3344229}, doi = {10.1145/3341981.3344229}, year = {2019}, date = {2019-09-01}, booktitle = {Proceedings of the 2019 acm sigir international conference on theory of information retrieval}, pages = {197–204}, publisher = {Association for Computing Machinery}, address = {New York}, abstract = {Recently false claims and misinformation have become rampant in the web, affecting election outcomes, societies and economies. Consequently, fact checking websites such as snopes.com and politifact.com are becoming popular. However, these websites require expert analysis which is slow and not scalable. Many recent works try to solve these challenges using machine learning models trained on a variety of features and a rich lexicon or more recently, deep neural networks to avoid feature engineering. In this paper, we propose hierarchical deep attention networks to learn embeddings for various latent aspects of news. Contrary to existing solutions which only apply word-level self-attention, our model jointly learns the latent aspect embeddings for classifying false claims by applying hierarchical attention. Using several manually annotated high quality datasets such as Politifact, Snopes and Fever we show that these learned aspect embeddings are strong predictors of false claims. We show that latent aspect embeddings learned from attention mechanisms improve the accuracy of false claim detection by up to 13.5% in terms of Macro F1 compared to a state-of-the-art attention mechanism guided by claim-text DeClarE. We also extract and visualize the evidence from the external articles which supports or disproves the claims}, note = {Pre SFI}, keywords = {Fake news, Hierarchical attention, Latent aspect embeddings, WP3: Media Content Production and Analysis}, pubstate = {published}, tppubtype = {conference} } Recently false claims and misinformation have become rampant in the web, affecting election outcomes, societies and economies. Consequently, fact checking websites such as snopes.com and politifact.com are becoming popular. However, these websites require expert analysis which is slow and not scalable. Many recent works try to solve these challenges using machine learning models trained on a variety of features and a rich lexicon or more recently, deep neural networks to avoid feature engineering. In this paper, we propose hierarchical deep attention networks to learn embeddings for various latent aspects of news. Contrary to existing solutions which only apply word-level self-attention, our model jointly learns the latent aspect embeddings for classifying false claims by applying hierarchical attention. Using several manually annotated high quality datasets such as Politifact, Snopes and Fever we show that these learned aspect embeddings are strong predictors of false claims. We show that latent aspect embeddings learned from attention mechanisms improve the accuracy of false claim detection by up to 13.5% in terms of Macro F1 compared to a state-of-the-art attention mechanism guided by claim-text DeClarE. We also extract and visualize the evidence from the external articles which supports or disproves the claims |
| Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches Conference Maurizio Ferrari Dacrema; Paolo Cremonesi; Dietmar Jannach Proceedings of the 2019 ACM Conference on Recommender Systems (RecSys 2019), Copenhagen, 2019, (Pre SFI). Abstract | BibTeX | Tags: Collaborative filtering, General and referance, Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement | Links: @conference{Dacrema2019, title = {Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches}, author = {Maurizio Ferrari Dacrema and Paolo Cremonesi and Dietmar Jannach}, url = {https://arxiv.org/pdf/1907.06902.pdf}, year = {2019}, date = {2019-08-16}, booktitle = {Proceedings of the 2019 ACM Conference on Recommender Systems (RecSys 2019)}, address = {Copenhagen}, abstract = {Deep learning techniques have become the method of choice for researchers working on algorithmic aspects of recommender systems. With the strongly increased interest in machine learning in general, it has, as a result, become difficult to keep track of what represents the state-of-the-art at the moment, e.g., for top-n recommendation tasks. At the same time, several recent publications point out problems in today’s research practice in applied machine learning, e.g., in terms of the reproducibility of the results or the choice of the baselines when proposing new models. In this work, we report the results of a systematic analysis of algorithmic proposals for top-n recommendation tasks. Specifically, we considered 18 algorithms that were presented at top-level research conferences in the last years. Only 7 of them could be reproduced with reasonable effort. For these methods, it however turned out that 6 of them can often be outperformed with comparably simple heuristic methods, e.g., based on nearest-neighbor or graph-based techniques. The remaining one clearly outperformed the baselines but did not consistently outperform a well-tuned nonneural linear ranking method. Overall, our work sheds light on a number of potential problems in today’s machine learning scholarship and calls for improved scientific practices in this area.}, note = {Pre SFI}, keywords = {Collaborative filtering, General and referance, Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {conference} } Deep learning techniques have become the method of choice for researchers working on algorithmic aspects of recommender systems. With the strongly increased interest in machine learning in general, it has, as a result, become difficult to keep track of what represents the state-of-the-art at the moment, e.g., for top-n recommendation tasks. At the same time, several recent publications point out problems in today’s research practice in applied machine learning, e.g., in terms of the reproducibility of the results or the choice of the baselines when proposing new models. In this work, we report the results of a systematic analysis of algorithmic proposals for top-n recommendation tasks. Specifically, we considered 18 algorithms that were presented at top-level research conferences in the last years. Only 7 of them could be reproduced with reasonable effort. For these methods, it however turned out that 6 of them can often be outperformed with comparably simple heuristic methods, e.g., based on nearest-neighbor or graph-based techniques. The remaining one clearly outperformed the baselines but did not consistently outperform a well-tuned nonneural linear ranking method. Overall, our work sheds light on a number of potential problems in today’s machine learning scholarship and calls for improved scientific practices in this area. |
| Answer set programming for judgment aggregation Conference Ronald de Haan; Marija Slavkovik Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, International Joint Conferences on Artificial Intelligence, 2019, (Pre SFI). Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links: @conference{deHaan2019, title = {Answer set programming for judgment aggregation}, author = {Ronald de Haan and Marija Slavkovik}, url = {https://www.ijcai.org/Proceedings/2019/0231.pdf}, year = {2019}, date = {2019-08-10}, booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence}, pages = {1668-1674}, publisher = {International Joint Conferences on Artificial Intelligence}, abstract = {Judgment aggregation (JA) studies how to aggregate truth valuations on logically related issues. Computing the outcome of aggregation procedures is notoriously computationally hard, which is the likely reason that no implementation of them exists as of yet. However, even hard problems sometimes need to be solved. The worst-case computational complexity of answer set programming (ASP) matches that of most problems in judgment aggregation. We take advantage of this and propose a natural and modular encoding of various judgment aggregation procedures and related problems in JA into ASP. With these encodings, we achieve two results: (1) paving the way towards constructing a wide range of new benchmark instances (from JA) for answer set solving algorithms; and (2) providing an automated tool for researchers in the area of judgment aggregation.}, note = {Pre SFI}, keywords = {WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {conference} } Judgment aggregation (JA) studies how to aggregate truth valuations on logically related issues. Computing the outcome of aggregation procedures is notoriously computationally hard, which is the likely reason that no implementation of them exists as of yet. However, even hard problems sometimes need to be solved. The worst-case computational complexity of answer set programming (ASP) matches that of most problems in judgment aggregation. We take advantage of this and propose a natural and modular encoding of various judgment aggregation procedures and related problems in JA into ASP. With these encodings, we achieve two results: (1) paving the way towards constructing a wide range of new benchmark instances (from JA) for answer set solving algorithms; and (2) providing an automated tool for researchers in the area of judgment aggregation. |
| Transparent, Scrutable and Explainable User Models for Personalized Recommendation Conference Krisztian Balog; Filip Radlinski; Shushan Arakelyan Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’19), 2019, (Pre SFI). Abstract | BibTeX | Tags: Explainability, Recommendations, Scrutability, Transparency, WP2: User Modeling Personalization and Engagement | Links: @conference{Balog2019, title = {Transparent, Scrutable and Explainable User Models for Personalized Recommendation}, author = {Krisztian Balog and Filip Radlinski and Shushan Arakelyan}, url = {https://dl.acm.org/doi/pdf/10.1145/3331184.3331211}, doi = {https://doi.org/10.1145/3331184.3331211}, year = {2019}, date = {2019-07-25}, booktitle = {Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’19)}, pages = {265–274}, abstract = {Most recommender systems base their recommendations on implicit or explicit item-level feedback provided by users. These item ratings are combined into a complex user model, which then predicts the suitability of other items. While effective, such methods have limited scrutability and transparency. For instance, if a user's interests change, then many item ratings would usually need to be modified to significantly shift the user's recommendations. Similarly, explaining how the system characterizes the user is impossible, short of presenting the entire list of known item ratings. In this paper, we present a new set-based recommendation technique that permits the user model to be explicitly presented to users in natural language, empowering users to understand recommendations made and improve the recommendations dynamically. While performing comparably to traditional collaborative filtering techniques in a standard static setting, our approach allows users to efficiently improve recommendations. Further, it makes it easier for the model to be validated and adjusted, building user trust and understanding.}, note = {Pre SFI}, keywords = {Explainability, Recommendations, Scrutability, Transparency, WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {conference} } Most recommender systems base their recommendations on implicit or explicit item-level feedback provided by users. These item ratings are combined into a complex user model, which then predicts the suitability of other items. While effective, such methods have limited scrutability and transparency. For instance, if a user's interests change, then many item ratings would usually need to be modified to significantly shift the user's recommendations. Similarly, explaining how the system characterizes the user is impossible, short of presenting the entire list of known item ratings. In this paper, we present a new set-based recommendation technique that permits the user model to be explicitly presented to users in natural language, empowering users to understand recommendations made and improve the recommendations dynamically. While performing comparably to traditional collaborative filtering techniques in a standard static setting, our approach allows users to efficiently improve recommendations. Further, it makes it easier for the model to be validated and adjusted, building user trust and understanding. |
| Journalism, Audiences and News Experience Book Chapter Irene Costera Meijer Wahl-Jorgensen, Karin; Hanitzsch, Thomas (Ed.): Chapter 25, pp. 389-405, Routledge, 2nd, 2019, ISBN: 9781315167497, (Pre SFI). Abstract | BibTeX | Tags: Journalism, News, WP1: Understanding Media Experiences | Links: @inbook{Meijer2019, title = {Journalism, Audiences and News Experience}, author = {Irene Costera Meijer }, editor = {Karin Wahl-Jorgensen and Thomas Hanitzsch }, url = {https://www.taylorfrancis.com/chapters/journalism-audiences-news-experience-irene-costera-meijer/e/10.4324/9781315167497-25}, doi = {10.4324/9781315167497-25}, isbn = {9781315167497}, year = {2019}, date = {2019-06-01}, pages = {389-405}, publisher = {Routledge}, edition = {2nd}, chapter = {25}, abstract = {This chapter focuses on the main analytical concepts used to study audiences in journalism and how they can be refined and extended by amplifying the field of journalism studies with insights and theories from neighboring disciplines. The use of audience engagement figures has led to concerns about the influence of Google, YouTube, and Facebook on news access and news availability. In terms of history, attention to changing user practices of news and journalism should be added to the discipline’s more common focus on narrating the history of particular news organizations or journalists. News reach, which is measured through newspaper circulation, ratings, and market shares, was primarily the concern of marketing departments. News users can be expected to act ethically by reflecting on the kind of friendship that journalism triggers in them, by the amount of time they choose to spend with these friends, and by taking on the responsibility for their own news participation.}, note = {Pre SFI}, keywords = {Journalism, News, WP1: Understanding Media Experiences}, pubstate = {published}, tppubtype = {inbook} } This chapter focuses on the main analytical concepts used to study audiences in journalism and how they can be refined and extended by amplifying the field of journalism studies with insights and theories from neighboring disciplines. The use of audience engagement figures has led to concerns about the influence of Google, YouTube, and Facebook on news access and news availability. In terms of history, attention to changing user practices of news and journalism should be added to the discipline’s more common focus on narrating the history of particular news organizations or journalists. News reach, which is measured through newspaper circulation, ratings, and market shares, was primarily the concern of marketing departments. News users can be expected to act ethically by reflecting on the kind of friendship that journalism triggers in them, by the amount of time they choose to spend with these friends, and by taking on the responsibility for their own news participation. |
| Supporting Journalistic News Angles with Models and Analogies Conference Bjørnar Tessem; Andreas Lothe Opdahl 2019 13th International Conference on Research Challenges in Information Science (RCIS), 2019, (Pre SFI). Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links: @conference{Tessem2019, title = {Supporting Journalistic News Angles with Models and Analogies}, author = {Bjørnar Tessem and Andreas Lothe Opdahl}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8877058}, doi = {10.1109/RCIS.2019.8877058}, year = {2019}, date = {2019-05-31}, booktitle = { 2019 13th International Conference on Research Challenges in Information Science (RCIS)}, pages = {1-7}, abstract = {News angles are approaches to content presentation in journalism, where the journalist chooses which facts of an event to present. The News Angler project investigates how to computationally support the creation and selection of original news angles for a news event based on information from big data sources. At least two creative approaches are possible. One is to maintain a library of well-known news angles represented in a suitable modeling language, matching published reports on a current event to news angles in order to identify possible angles that have not yet been used. A second approach is not to represent news angles explicitly, instead matching the current event with previous events, and transferring angles from past to present reports by similarity and analogy. Both approaches are described and technologies needed to proceed in either direction are discussed.}, note = {Pre SFI}, keywords = {WP3: Media Content Production and Analysis}, pubstate = {published}, tppubtype = {conference} } News angles are approaches to content presentation in journalism, where the journalist chooses which facts of an event to present. The News Angler project investigates how to computationally support the creation and selection of original news angles for a news event based on information from big data sources. At least two creative approaches are possible. One is to maintain a library of well-known news angles represented in a suitable modeling language, matching published reports on a current event to news angles in order to identify possible angles that have not yet been used. A second approach is not to represent news angles explicitly, instead matching the current event with previous events, and transferring angles from past to present reports by similarity and analogy. Both approaches are described and technologies needed to proceed in either direction are discussed. |
| Participatory Design of VR Scenarios for Exposure Therapy Conference Eivind Flobak; Jo Dugstad Wake; Joakim Vindenes; Smiti Kahlon; T. Nordgreen; Frode Guribye Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI '19), (Paper 569), New York, 2019, (Pre SFI). Abstract | BibTeX | Tags: WP4: Media Content Interaction and Accessibility | Links: @conference{Flobak2019, title = {Participatory Design of VR Scenarios for Exposure Therapy}, author = {Eivind Flobak and Jo Dugstad Wake and Joakim Vindenes and Smiti Kahlon and T. Nordgreen and Frode Guribye}, url = {https://www.researchgate.net/publication/330205387_Participatory_Design_of_VR_Scenarios_for_Exposure_Therapy}, doi = {10.1145/3290605.3300799 }, year = {2019}, date = {2019-05-01}, booktitle = {Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI '19)}, number = {Paper 569}, address = {New York}, abstract = {Virtual reality (VR) applications for exposure therapy predominantly use computer-generated imagery to create controlled environments in which users can be exposed to their fears. Creating 3D animations, however, is demanding and time-consuming. This paper presents a participatory approach for prototyping VR scenarios that are enabled by 360° video and grounded in lived experiences. We organized a participa-tory workshop with adolescents to prototype such scenarios, consisting of iterative phases of ideation, storyboarding, live-action plays recorded by a 360° camera, and group evaluation. Through an analysis of the participants' interactions, we outline how they worked to design prototypes that depict situations relevant to those with a fear of public speaking. Our analysis also explores how participants used their experiences and refections as resources for design. Six clinical psychologists evaluated the prototypes from the workshop and concluded they were viable therapeutic tools, emphasizing the immer-sive, realistic experience they presented. We argue that our approach makes the design of VR scenarios more accessible.}, note = {Pre SFI}, keywords = {WP4: Media Content Interaction and Accessibility}, pubstate = {published}, tppubtype = {conference} } Virtual reality (VR) applications for exposure therapy predominantly use computer-generated imagery to create controlled environments in which users can be exposed to their fears. Creating 3D animations, however, is demanding and time-consuming. This paper presents a participatory approach for prototyping VR scenarios that are enabled by 360° video and grounded in lived experiences. We organized a participa-tory workshop with adolescents to prototype such scenarios, consisting of iterative phases of ideation, storyboarding, live-action plays recorded by a 360° camera, and group evaluation. Through an analysis of the participants' interactions, we outline how they worked to design prototypes that depict situations relevant to those with a fear of public speaking. Our analysis also explores how participants used their experiences and refections as resources for design. Six clinical psychologists evaluated the prototypes from the workshop and concluded they were viable therapeutic tools, emphasizing the immer-sive, realistic experience they presented. We argue that our approach makes the design of VR scenarios more accessible. |
| Journalism between the state and the market Book Helle Sjøvaag Routledge, New York, 2019, ISBN: 9781138543348, (Pre SFI). Abstract | BibTeX | Tags: Journalism, Market, WP2: User Modeling Personalization and Engagement | Links: @book{Sjøvaag2019, title = {Journalism between the state and the market}, author = {Helle Sjøvaag}, url = {https://www.researchgate.net/publication/332449932_Journalism_Between_the_State_and_the_Market}, isbn = {9781138543348}, year = {2019}, date = {2019-04-24}, publisher = {Routledge}, address = {New York}, abstract = {Using the Nordic media model as an empirical backdrop, Journalism Between the State and the Market defines and analyzes journalism’s fundamental problem: its shifting location between the state and the market. This book examines how this distance is decreasing as journalism steps closer to both the market (algorithmically monetizing audiences) and the state (lobbying governments for subsidies and attacking public service broadcasting). The book analyzes journalism’s negotiated position between the market and the state in the age of disruptions, offering a theoretical foundation that seeks to account for the structural conditions of journalism in the digital age. For scholars, graduates and students in journalism, news sociology and media and communication studies, Journalism Between the State and the Market provides a theoretical perspective that can be used as a valuable tool when studying and observing the current developments in journalism.}, note = {Pre SFI}, keywords = {Journalism, Market, WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {book} } Using the Nordic media model as an empirical backdrop, Journalism Between the State and the Market defines and analyzes journalism’s fundamental problem: its shifting location between the state and the market. This book examines how this distance is decreasing as journalism steps closer to both the market (algorithmically monetizing audiences) and the state (lobbying governments for subsidies and attacking public service broadcasting). The book analyzes journalism’s negotiated position between the market and the state in the age of disruptions, offering a theoretical foundation that seeks to account for the structural conditions of journalism in the digital age. For scholars, graduates and students in journalism, news sociology and media and communication studies, Journalism Between the State and the Market provides a theoretical perspective that can be used as a valuable tool when studying and observing the current developments in journalism. |
| Building Jiminy Cricket: An architecture for moral agreements among stakeholders Conference Beishui Liao; Marija Slavkovik; Leendert van der Torre Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, 2019, (Pre SFI). Abstract | BibTeX | Tags: Artificial Intelligence, WP2: User Modeling Personalization and Engagement | Links: @conference{Liao2019, title = {Building Jiminy Cricket: An architecture for moral agreements among stakeholders}, author = {Beishui Liao and Marija Slavkovik and Leendert van der Torre}, url = {https://arxiv.org/pdf/1812.04741.pdf}, year = {2019}, date = {2019-03-07}, booktitle = {Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society}, pages = {147–153}, abstract = {An autonomous system is constructed by a manufacturer, operates in a society subject to norms and laws, and is interacting with end-users. We address the challenge of how the moral values and views of all stakeholders can be integrated and reflected in the moral behaviour of the autonomous system. We propose an artificial moral agent architecture that uses techniques from normative systems and formal argumentation to reach moral agreements among stakeholders. We show how our architecture can be used not only for ethical practical reasoning and collaborative decision-making, but also for the explanation of such moral behavior.}, note = {Pre SFI}, keywords = {Artificial Intelligence, WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {conference} } An autonomous system is constructed by a manufacturer, operates in a society subject to norms and laws, and is interacting with end-users. We address the challenge of how the moral values and views of all stakeholders can be integrated and reflected in the moral behaviour of the autonomous system. We propose an artificial moral agent architecture that uses techniques from normative systems and formal argumentation to reach moral agreements among stakeholders. We show how our architecture can be used not only for ethical practical reasoning and collaborative decision-making, but also for the explanation of such moral behavior. |
2018 |
| Is public service broadcasting a threat to commercial media? Journal Article Helle Sjøvaag; Truls André Pedersen; Thomas Owren Media, Culture & Society, 46 (1), pp. 808-827, 2018, (Pre SFI). Abstract | BibTeX | Tags: Commercial media, Content analysis, Latent Dirichlet allocationand Engagement, Media Diversity, Media Policy, Online news, Publice Service Broadcasting, WP2: User Modeling Personalization and Engagement | Links: @article{Sjøvaag2018c, title = {Is public service broadcasting a threat to commercial media?}, author = {Helle Sjøvaag and Truls André Pedersen and Thomas Owren}, url = {https://journals.sagepub.com/doi/pdf/10.1177/0163443718818354}, doi = {https://doi.org/10.1177/0163443718818354}, year = {2018}, date = {2018-12-20}, journal = {Media, Culture & Society}, volume = {46}, number = {1}, pages = {808-827}, abstract = {This article asks to what extent public service broadcasting’s online news service resembles that of commercial media. The context of this inquiry is claims of ‘out-crowding’ facing public service broadcasters across Europe. In Norway, commercial players in this debate accuse the public service broadcaster, NRK, of being too similar to competitors in the private sector for commercial operators to attain sustainable revenues in the online realm. To ascertain the extent to what these claims are warranted, this article compares NRK’s online content with that of nine commercial competitors in national and local markets, using a hybrid methodological approach combining quantitative content analysis with Latent Dirichlet allocation, analysing in excess of 115,000 documents. Findings show that commercial operators resemble each other more than they do NRK, indicating closer competition in the commercial segment than between the public service broadcaster and market players.}, note = {Pre SFI}, keywords = {Commercial media, Content analysis, Latent Dirichlet allocationand Engagement, Media Diversity, Media Policy, Online news, Publice Service Broadcasting, WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {article} } This article asks to what extent public service broadcasting’s online news service resembles that of commercial media. The context of this inquiry is claims of ‘out-crowding’ facing public service broadcasters across Europe. In Norway, commercial players in this debate accuse the public service broadcaster, NRK, of being too similar to competitors in the private sector for commercial operators to attain sustainable revenues in the online realm. To ascertain the extent to what these claims are warranted, this article compares NRK’s online content with that of nine commercial competitors in national and local markets, using a hybrid methodological approach combining quantitative content analysis with Latent Dirichlet allocation, analysing in excess of 115,000 documents. Findings show that commercial operators resemble each other more than they do NRK, indicating closer competition in the commercial segment than between the public service broadcaster and market players. |
| Mediasync Report 2015: Evaluating timed playback of HTML5 Media Technical Report Njål Borch; Ingar Mæhlum Arntzen 2018, (Pre SFI). BibTeX | Tags: WP4: Media Content Interaction and Accessibility | Links: @techreport{Borch2015, title = {Mediasync Report 2015: Evaluating timed playback of HTML5 Media}, author = {Njål Borch and Ingar Mæhlum Arntzen}, url = {https://norceresearch.brage.unit.no/norceresearch-xmlui/bitstream/handle/11250/2711974/Norut_Tromso_rapport_28-2015.pdf?sequence=2}, year = {2018}, date = {2018-12-18}, note = {Pre SFI}, keywords = {WP4: Media Content Interaction and Accessibility}, pubstate = {published}, tppubtype = {techreport} } |
| On the distinction between implicit and explicit ethical agency Conference Sjur Dyrkolbotn; Truls Pedersen; Marija Slavkovik Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society (AIES '18), 2018, (Pre SFI). Abstract | BibTeX | Tags: Agency, Artificial Intelligence, Autonomy, Epistemology, Ethics, WP2: User Modeling Personalization and Engagement | Links: @conference{Dyrkolbotn2018, title = {On the distinction between implicit and explicit ethical agency}, author = {Sjur Dyrkolbotn and Truls Pedersen and Marija Slavkovik}, url = {https://dl.acm.org/doi/pdf/10.1145/3278721.3278769}, doi = {https://doi.org/10.1145/3278721.3278769}, year = {2018}, date = {2018-12-01}, booktitle = {Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society (AIES '18)}, pages = {74–80}, abstract = {With recent advances in artificial intelligence and the rapidly increasing importance of autonomous intelligent systems in society, it is becoming clear that artificial agents will have to be designed to comply with complex ethical standards. As we work to develop moral machines, we also push the boundaries of existing legal categories. The most pressing question is what kind of ethical decision-making our machines are actually able to engage in. Both in law and in ethics, the concept of agency forms a basis for further legal and ethical categorisations, pertaining to decision-making ability. Hence, without a cross-disciplinary understanding of what we mean by ethical agency in machines, the question of responsibility and liability cannot be clearly addressed. Here we make first steps towards a comprehensive definition, by suggesting ways to distinguish between implicit and explicit forms of ethical agency.}, note = {Pre SFI}, keywords = {Agency, Artificial Intelligence, Autonomy, Epistemology, Ethics, WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {conference} } With recent advances in artificial intelligence and the rapidly increasing importance of autonomous intelligent systems in society, it is becoming clear that artificial agents will have to be designed to comply with complex ethical standards. As we work to develop moral machines, we also push the boundaries of existing legal categories. The most pressing question is what kind of ethical decision-making our machines are actually able to engage in. Both in law and in ethics, the concept of agency forms a basis for further legal and ethical categorisations, pertaining to decision-making ability. Hence, without a cross-disciplinary understanding of what we mean by ethical agency in machines, the question of responsibility and liability cannot be clearly addressed. Here we make first steps towards a comprehensive definition, by suggesting ways to distinguish between implicit and explicit forms of ethical agency. |
| AdapTable: Extending Reach over Large Tabletops Through Flexible Multi-Display Configuration. Proceeding Y. Kudo; K. Takashima; Morten Fjeld; Y. Kitamura, 2018, (Pre SFI). BibTeX | Tags: WP4: Media Content Interaction and Accessibility | Links: @proceedings{Kudo2018, title = { AdapTable: Extending Reach over Large Tabletops Through Flexible Multi-Display Configuration.}, author = {Y. Kudo and K. Takashima and Morten Fjeld and Y. Kitamura, }, url = {https://dl.acm.org/doi/pdf/10.1145/3279778.3279779 https://www.youtube.com/watch?v=HG_4COsWGDM}, year = {2018}, date = {2018-11-17}, note = {Pre SFI}, keywords = {WP4: Media Content Interaction and Accessibility}, pubstate = {published}, tppubtype = {proceedings} } |
| Towards a big data platform for news angles Workshop Marc Gallofré Ocaña; Lars Nyre; Andreas Lothe Opdahl; Bjørnar Tessem; Christoph Trattner; Csaba Veres Norwegian Big Data Symposium 2018, 2018, (Pre SFI). Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links: @workshop{Ocaña2018, title = {Towards a big data platform for news angles}, author = {Marc Gallofré Ocaña and Lars Nyre and Andreas Lothe Opdahl and Bjørnar Tessem and Christoph Trattner and Csaba Veres}, url = {https://www.researchgate.net/publication/332274562_Towards_a_Big_Data_Platform_for_News_Angles}, year = {2018}, date = {2018-11-01}, booktitle = {Norwegian Big Data Symposium 2018}, abstract = {Finding good angles on news events is a central journalistic and editorial skill. As news work becomes increasingly computer-assisted and big-data based, journalistic tools therefore need to become better able to support news angles too. This paper outlines a big-data platform that is able to suggest appropriate angles on news events to journalists. We first clarify and discuss the central characteristics of news angles. We then proceed to outline a big-data architecture that can propose news angles. Important areas for further work include: representing news angles formally; identifying interesting and unexpected angles on unfolding events; and designing a big-data architecture that works on a global scale. }, note = {Pre SFI}, keywords = {WP3: Media Content Production and Analysis}, pubstate = {published}, tppubtype = {workshop} } Finding good angles on news events is a central journalistic and editorial skill. As news work becomes increasingly computer-assisted and big-data based, journalistic tools therefore need to become better able to support news angles too. This paper outlines a big-data platform that is able to suggest appropriate angles on news events to journalists. We first clarify and discuss the central characteristics of news angles. We then proceed to outline a big-data architecture that can propose news angles. Important areas for further work include: representing news angles formally; identifying interesting and unexpected angles on unfolding events; and designing a big-data architecture that works on a global scale. |
| Female voices in the news: Structural conditions of gender representations in Norwegian newspapers Journal Article Helle Sjøvaag; Truls André Pedersen Journalism & Mass Communication Quarterly, 96 (1), pp. 215-238, 2018, (Pre SFI). Abstract | BibTeX | Tags: Computional content analysis, Diversity, Gender, Media structures, WP2: User Modeling Personalization and Engagement | Links: @article{Sjøvaag2018b, title = {Female voices in the news: Structural conditions of gender representations in Norwegian newspapers}, author = {Helle Sjøvaag and Truls André Pedersen}, url = {https://journals.sagepub.com/doi/pdf/10.1177/1077699018789885}, doi = {https://doi.org/10.1177/1077699018789885}, year = {2018}, date = {2018-08-21}, journal = {Journalism & Mass Communication Quarterly}, volume = {96}, number = {1}, pages = {215-238}, abstract = {The article presents a hybrid analysis combining manual content analysis of 9,131 sources in 5,544 news stories across 75 publications, with computational gender recognition producing 551,102 names from 320,228 articles across 125 newspapers. The article investigates the significance of structural features for the presence of women in the news. Results show female sources are only equal to men as ordinary citizens and children, and only in lifestyle content. Among the structural features examined, only local distribution and a circulation less than 5,000 exhibit improvements in female representation. Ownership, distribution frequency, market position, and direct press support had little or no effect.}, note = {Pre SFI}, keywords = {Computional content analysis, Diversity, Gender, Media structures, WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {article} } The article presents a hybrid analysis combining manual content analysis of 9,131 sources in 5,544 news stories across 75 publications, with computational gender recognition producing 551,102 names from 320,228 articles across 125 newspapers. The article investigates the significance of structural features for the presence of women in the news. Results show female sources are only equal to men as ordinary citizens and children, and only in lifestyle content. Among the structural features examined, only local distribution and a circulation less than 5,000 exhibit improvements in female representation. Ownership, distribution frequency, market position, and direct press support had little or no effect. |
| Diachronic word embeddings and semantic shifts: a survey Proceeding A Kutuzov; Lilja Øvrelid; T Szymanski; Erik Velldal 2018, (Pre SFI). BibTeX | Tags: WP5: Norwegian Language Technologies | Links: @proceedings{Kutuzov2018, title = {Diachronic word embeddings and semantic shifts: a survey}, author = {A Kutuzov and Lilja Øvrelid and T Szymanski and Erik Velldal}, url = {https://www.aclweb.org/anthology/C18-1117/}, year = {2018}, date = {2018-08-01}, note = {Pre SFI}, keywords = {WP5: Norwegian Language Technologies}, pubstate = {published}, tppubtype = {proceedings} } |
| WristOrigami: Exploring foldable design for multi-display smartwatch Proceeding K, Zhu; Morten Fjeld; A Ülüner 2018, (Pre SFI). BibTeX | Tags: WP4: Media Content Interaction and Accessibility | Links: @proceedings{Zhu2018, title = {WristOrigami: Exploring foldable design for multi-display smartwatch}, author = {K, Zhu and Morten Fjeld and A Ülüner}, url = {https://dl.acm.org/doi/pdf/10.1145/3196709.3196713 https://www.youtube.com/watch?v=1_2D79zntIk}, year = {2018}, date = {2018-06-09}, note = {Pre SFI}, keywords = {WP4: Media Content Interaction and Accessibility}, pubstate = {published}, tppubtype = {proceedings} } |
| Challenges and opportunities within personal life archives Conference Duc-Tien Dang Nguyen; Michael Alexander Riegler; Liting Zhou; Cathal Gurrin Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, 2018, (Pre SFI). Abstract | BibTeX | Tags: Lifelogging, Personal Life Archiv, Search Engine, WP3: Media Content Production and Analysis | Links: @conference{Nguyen2018, title = {Challenges and opportunities within personal life archives}, author = {Duc-Tien Dang Nguyen and Michael Alexander Riegler and Liting Zhou and Cathal Gurrin}, url = {https://www.researchgate.net/publication/325706506_Challenges_and_Opportunities_within_Personal_Life_Archives}, doi = {10.1145/3206025.3206040}, year = {2018}, date = {2018-06-01}, booktitle = {Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval}, pages = {335-343}, abstract = {Nowadays, almost everyone holds some form or other of a personal life archive. Automatically maintaining such an archive is an activity that is becoming increasingly common, however without automatic support the users will quickly be overwhelmed by the volume of data and will miss out on the potential benefits that lifelogs provide. In this paper we give an overview of the current status of lifelog research and propose a concept for exploring these archives. We motivate the need for new methodologies for indexing data, organizing content and supporting information access. Finally we will describe challenges to be addressed and give an overview of initial steps that have to be taken, to address the challenges of organising and searching personal life archives.}, note = {Pre SFI}, keywords = {Lifelogging, Personal Life Archiv, Search Engine, WP3: Media Content Production and Analysis}, pubstate = {published}, tppubtype = {conference} } Nowadays, almost everyone holds some form or other of a personal life archive. Automatically maintaining such an archive is an activity that is becoming increasingly common, however without automatic support the users will quickly be overwhelmed by the volume of data and will miss out on the potential benefits that lifelogs provide. In this paper we give an overview of the current status of lifelog research and propose a concept for exploring these archives. We motivate the need for new methodologies for indexing data, organizing content and supporting information access. Finally we will describe challenges to be addressed and give an overview of initial steps that have to be taken, to address the challenges of organising and searching personal life archives. |
| Neural embeddings for news events Conference Vinay Setty; Katja Hose The 41st international acm sigir conference on research development in information retrieval, Association for Computing Machinery Association for Computing Machinery, New York, 2018, (Pre SFI). Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links: @conference{Setty2018, title = {Neural embeddings for news events}, author = {Vinay Setty and Katja Hose}, url = {https://dl.acm.org/doi/pdf/10.1145/3209978.3210136}, doi = {10.1145/3209978.3210136}, year = {2018}, date = {2018-06-01}, booktitle = {The 41st international acm sigir conference on research development in information retrieval}, pages = {1013–1016}, publisher = {Association for Computing Machinery}, address = {New York}, organization = {Association for Computing Machinery}, abstract = {Representation of news events as latent feature vectors is essential for several tasks, such as news recommendation, news event linking, etc. However, representations proposed in the past fail to capture the complex network structure of news events. In this paper we propose Event2Vec, a novel way to learn latent feature vectors for news events using a network. We use recently proposed network embedding techniques, which are proven to be very effective for various prediction tasks in networks. As events involve different classes of nodes, such as named entities, temporal information, etc, general purpose network embeddings are agnostic to event semantics. To address this problem, we propose biased random walks that are tailored to capture the neighborhoods of news events in event networks. We then show that these learned embeddings are effective for news event recommendation and news event linking tasks using strong baselines, such as vanilla Node2Vec, and other state-of-the-art graph-based event ranking techniques.}, note = {Pre SFI}, keywords = {WP3: Media Content Production and Analysis}, pubstate = {published}, tppubtype = {conference} } Representation of news events as latent feature vectors is essential for several tasks, such as news recommendation, news event linking, etc. However, representations proposed in the past fail to capture the complex network structure of news events. In this paper we propose Event2Vec, a novel way to learn latent feature vectors for news events using a network. We use recently proposed network embedding techniques, which are proven to be very effective for various prediction tasks in networks. As events involve different classes of nodes, such as named entities, temporal information, etc, general purpose network embeddings are agnostic to event semantics. To address this problem, we propose biased random walks that are tailored to capture the neighborhoods of news events in event networks. We then show that these learned embeddings are effective for news event recommendation and news event linking tasks using strong baselines, such as vanilla Node2Vec, and other state-of-the-art graph-based event ranking techniques. |
| Movespace: on-body athletic interaction for running and cycling Journal Article V. Vechev; A. Dancu; S Perrault; Q. Roy; Morten Fjeld; S Zhao 2018, (Pre SFI). BibTeX | Tags: WP4: Media Content Interaction and Accessibility | Links: @article{Vechev2018, title = {Movespace: on-body athletic interaction for running and cycling}, author = {V. Vechev and A. Dancu and S Perrault and Q. Roy and Morten Fjeld and S Zhao }, url = {https://dl.acm.org/doi/pdf/10.1145/3206505.3206527 https://www.youtube.com/watch?v=1_u4Zm4F7I0}, year = {2018}, date = {2018-05-29}, note = {Pre SFI}, keywords = {WP4: Media Content Interaction and Accessibility}, pubstate = {published}, tppubtype = {article} } |
NoReC: The Norwegian Review Corpus Proceeding Erik Velldal; Lilja Øvrelid; Eivind Alexander Bergem; Cathrine Stadsnes; Samia Touileb; Fredrik Jørgensen 2018, (Pre SFI). Abstract | BibTeX | Tags: WP5: Norwegian Language Technologies @proceedings{Velldal2018, title = {NoReC: The Norwegian Review Corpus}, author = {Erik Velldal and Lilja Øvrelid and Eivind Alexander Bergem and Cathrine Stadsnes and Samia Touileb and Fredrik Jørgensen}, year = {2018}, date = {2018-05-12}, abstract = {https://repo.clarino.uib.no/xmlui/handle/11509/124}, note = {Pre SFI}, keywords = {WP5: Norwegian Language Technologies}, pubstate = {published}, tppubtype = {proceedings} } https://repo.clarino.uib.no/xmlui/handle/11509/124 |
| Media Synchronization on the Web. In: MediaSync Book Chapter Ingar Mæhlum Arntzen; Njål Borch; François Daoust 2018, (Pre SFI). BibTeX | Tags: WP4: Media Content Interaction and Accessibility | Links: @inbook{Arntzen2018, title = {Media Synchronization on the Web. In: MediaSync}, author = {Ingar Mæhlum Arntzen and Njål Borch and François Daoust}, url = {https://www.w3.org/community/webtiming/files/2018/05/arntzen_mediasync_web_author_edition.pdf}, year = {2018}, date = {2018-05-07}, note = {Pre SFI}, keywords = {WP4: Media Content Interaction and Accessibility}, pubstate = {published}, tppubtype = {inbook} } |
| AUGUR: forecasting the emergence of new research topics Conference Angelo Antonio Salatino; Francesco Osborne; Enrico Motta Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries, 2018, (Pre SFI). Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links: @conference{Salatino2018, title = {AUGUR: forecasting the emergence of new research topics}, author = {Angelo Antonio Salatino and Francesco Osborne and Enrico Motta}, url = {https://www.researchgate.net/publication/325492541_AUGUR_Forecasting_the_Emergence_of_New_Research_Topics}, year = {2018}, date = {2018-05-01}, booktitle = {Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries}, pages = {303-312}, abstract = {Being able to rapidly recognise new research trends is strategic for many stakeholders, including universities, institutional funding bodies, academic publishers and companies. The literature presents several approaches to identifying the emergence of new research topics, which rely on the assumption that the topic is already exhibiting a certain degree of popularity and consistently referred to by a community of researchers. However, detecting the emergence of a new research area at an embryonic stage, i.e., before the topic has been consistently labelled by a community of researchers and associated with a number of publications, is still an open challenge. We address this issue by introducing Augur, a novel approach to the early detection of research topics. Augur analyses the diachronic relationships between research areas and is able to detect clusters of topics that exhibit dynamics correlated with the emergence of new research topics. Here we also present the Advanced Clique Percolation Method (ACPM), a new community detection algorithm developed specifically for supporting this task. Augur was evaluated on a gold standard of 1,408 debutant topics in the 2000-2011 interval and outperformed four alternative approaches in terms of both precision and recall.}, note = {Pre SFI}, keywords = {WP3: Media Content Production and Analysis}, pubstate = {published}, tppubtype = {conference} } Being able to rapidly recognise new research trends is strategic for many stakeholders, including universities, institutional funding bodies, academic publishers and companies. The literature presents several approaches to identifying the emergence of new research topics, which rely on the assumption that the topic is already exhibiting a certain degree of popularity and consistently referred to by a community of researchers. However, detecting the emergence of a new research area at an embryonic stage, i.e., before the topic has been consistently labelled by a community of researchers and associated with a number of publications, is still an open challenge. We address this issue by introducing Augur, a novel approach to the early detection of research topics. Augur analyses the diachronic relationships between research areas and is able to detect clusters of topics that exhibit dynamics correlated with the emergence of new research topics. Here we also present the Advanced Clique Percolation Method (ACPM), a new community detection algorithm developed specifically for supporting this task. Augur was evaluated on a gold standard of 1,408 debutant topics in the 2000-2011 interval and outperformed four alternative approaches in terms of both precision and recall. |
| Approximately Informed, Occasionally Monitorial? Reconsidering Normative Citizen Ideals. Journal Article Brita Ytre-Arne; Hallvard Moe International Journal of Press/Politics, 23 (2), pp. 227–246, 2018, (Pre SFI). Abstract | BibTeX | Tags: Citizens, Democracy, Democratic Realism, Media Audiences, News, Public Sphere, WP1: Understanding Media Experiences | Links: @article{Arne2018, title = {Approximately Informed, Occasionally Monitorial? Reconsidering Normative Citizen Ideals.}, author = {Brita Ytre-Arne and Hallvard Moe}, url = {https://journals.sagepub.com/doi/pdf/10.1177/1940161218771903}, doi = {10.1177/1940161218771903}, year = {2018}, date = {2018-04-27}, journal = {International Journal of Press/Politics}, volume = {23}, number = {2}, pages = {227–246}, abstract = {This article identifies gaps between normative ideals and realistic accounts of news use in democracy today. Starting from the widespread but unrealistic ideal of the informed citizen, and its more realistic development through notions of the monitorial citizen, we analyze comprehensive qualitative data on news users’ experiences. We describe these news users as approximately informed, occasionally monitorial. This description emphasizes the limited, shifting, and partial figurations of societal information that citizens are able to obtain through their use of journalistic and social media, and thereby challenges normative ideals. How do monitorial ideals function when the citizens are only occasionally on guard? By zooming in on three key gaps between even a less demanding ideal and actual practices in news use, we underline the need to further reconceptualize our expectations of citizens’ news use.}, note = {Pre SFI}, keywords = {Citizens, Democracy, Democratic Realism, Media Audiences, News, Public Sphere, WP1: Understanding Media Experiences}, pubstate = {published}, tppubtype = {article} } This article identifies gaps between normative ideals and realistic accounts of news use in democracy today. Starting from the widespread but unrealistic ideal of the informed citizen, and its more realistic development through notions of the monitorial citizen, we analyze comprehensive qualitative data on news users’ experiences. We describe these news users as approximately informed, occasionally monitorial. This description emphasizes the limited, shifting, and partial figurations of societal information that citizens are able to obtain through their use of journalistic and social media, and thereby challenges normative ideals. How do monitorial ideals function when the citizens are only occasionally on guard? By zooming in on three key gaps between even a less demanding ideal and actual practices in news use, we underline the need to further reconceptualize our expectations of citizens’ news use. |
| The hyperlinked Scandinavian news ecology: The unequal terms forged by the structural properties of digitalisation Journal Article Helle Sjøvaag; Eirik Stavelin; Michael Karlsson; Aske Kammer Digital Journalism, 7 (4), pp. 507-531, 2018, (Pre SFI). Abstract | BibTeX | Tags: Digital News Ecology, Hyperlinks, Media ownership, Network analysis, News geographies, WP2: User Modeling Personalization and Engagement | Links: @article{Sjøvaag2018, title = {The hyperlinked Scandinavian news ecology: The unequal terms forged by the structural properties of digitalisation}, author = {Helle Sjøvaag and Eirik Stavelin and Michael Karlsson and Aske Kammer}, url = {https://www.tandfonline.com/doi/epub/10.1080/21670811.2018.1454335?needAccess=true}, doi = {https://doi.org/10.1080/21670811.2018.1454335}, year = {2018}, date = {2018-04-06}, journal = {Digital Journalism}, volume = {7}, number = {4}, pages = {507-531}, abstract = {The article presents a network analysis of 22,861,013 geocoded external hyperlinks, collected from 230 Danish, 220 Norwegian and 208 Swedish news websites in 2016. The analysis asks what the structural properties of the Scandinavian media systems—including its geography and ownership structures—mean for news outlets’ centrality within the hyperlinked news ecology. The analysis finds that whereas incumbent legacy media occupy central positions, about one third of the network is absent from the hyperlinked interaction, primarily local, independently owned newspapers. A multiple linear regression analysis shows that national distribution and corporate ownership correlates to network centrality more than other predictors. As brokers in the network consist of the large, legacy, capital-based news organisations, hyperlink connectivity is primarily characterised by proximity to the centres of power, corporate ownership, agenda setting incumbency and national distribution.}, note = {Pre SFI}, keywords = {Digital News Ecology, Hyperlinks, Media ownership, Network analysis, News geographies, WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {article} } The article presents a network analysis of 22,861,013 geocoded external hyperlinks, collected from 230 Danish, 220 Norwegian and 208 Swedish news websites in 2016. The analysis asks what the structural properties of the Scandinavian media systems—including its geography and ownership structures—mean for news outlets’ centrality within the hyperlinked news ecology. The analysis finds that whereas incumbent legacy media occupy central positions, about one third of the network is absent from the hyperlinked interaction, primarily local, independently owned newspapers. A multiple linear regression analysis shows that national distribution and corporate ownership correlates to network centrality more than other predictors. As brokers in the network consist of the large, legacy, capital-based news organisations, hyperlink connectivity is primarily characterised by proximity to the centres of power, corporate ownership, agenda setting incumbency and national distribution. |
| Evaluation of Session-based Recommendation Algorithms Journal Article Malte Ludewig; Dietmar Jannach User-Modeling and User-Adapted Interaction, 28 (4-5), pp. 331-390, 2018, (Pre SFI). Abstract | BibTeX | Tags: Evaluation, General and referance, Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement | Links: @article{Ludewig2018, title = {Evaluation of Session-based Recommendation Algorithms}, author = {Malte Ludewig and Dietmar Jannach}, url = {https://arxiv.org/pdf/1803.09587.pdf}, doi = {10.1007/s11257-018-9209-6}, year = {2018}, date = {2018-03-26}, journal = {User-Modeling and User-Adapted Interaction}, volume = {28}, number = {4-5}, pages = {331-390}, abstract = {Recommender systems help users find relevant items of interest, for example on e-commerce or media streaming sites. Most academic research is concerned with approaches that personalize the recommendations according to long-term user profiles. In many real-world applications, however, such long-term profiles often do not exist and recommendations therefore have to be made solely based on the observed behavior of a user during an ongoing session. Given the high practical relevance of the problem, an increased interest in this problem can be observed in recent years, leading to a number of proposals for session-based recommendation algorithms that typically aim to predict the user's immediate next actions. In this work, we present the results of an in-depth performance comparison of a number of such algorithms, using a variety of datasets and evaluation measures. Our comparison includes the most recent approaches based on recurrent neural networks like GRU4REC, factorized Markov model approaches such as FISM or FOSSIL, as well as simpler methods based, e.g., on nearest neighbor schemes. Our experiments reveal that algorithms of this latter class, despite their sometimes almost trivial nature, often perform equally well or significantly better than today's more complex approaches based on deep neural networks. Our results therefore suggest that there is substantial room for improvement regarding the development of more sophisticated session-based recommendation algorithms.}, note = {Pre SFI}, keywords = {Evaluation, General and referance, Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {article} } Recommender systems help users find relevant items of interest, for example on e-commerce or media streaming sites. Most academic research is concerned with approaches that personalize the recommendations according to long-term user profiles. In many real-world applications, however, such long-term profiles often do not exist and recommendations therefore have to be made solely based on the observed behavior of a user during an ongoing session. Given the high practical relevance of the problem, an increased interest in this problem can be observed in recent years, leading to a number of proposals for session-based recommendation algorithms that typically aim to predict the user's immediate next actions. In this work, we present the results of an in-depth performance comparison of a number of such algorithms, using a variety of datasets and evaluation measures. Our comparison includes the most recent approaches based on recurrent neural networks like GRU4REC, factorized Markov model approaches such as FISM or FOSSIL, as well as simpler methods based, e.g., on nearest neighbor schemes. Our experiments reveal that algorithms of this latter class, despite their sometimes almost trivial nature, often perform equally well or significantly better than today's more complex approaches based on deep neural networks. Our results therefore suggest that there is substantial room for improvement regarding the development of more sophisticated session-based recommendation algorithms. |
| Sequence-Aware Recommender Systems Journal Article Massimo Quadrana; Paolo Cremonesi; Dietmar Jannach ACM Computing Surveys, 51 (4), pp. 1-35, 2018, (Pre SFI). Abstract | BibTeX | Tags: Collaborative filtering, Computing Methodology, Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement | Links: @article{Quadrana2018, title = {Sequence-Aware Recommender Systems}, author = {Massimo Quadrana and Paolo Cremonesi and Dietmar Jannach}, url = {https://arxiv.org/pdf/1802.08452.pdf}, year = {2018}, date = {2018-02-23}, journal = {ACM Computing Surveys}, volume = {51}, number = {4}, pages = {1-35}, abstract = {Recommender systems are one of the most successful applications of data mining and machine learning technology in practice. Academic research in the field is historically often based on the matrix completion problem formulation, where for each user-item-pair only one interaction (e.g., a rating) is considered. In many application domains, however, multiple user-item interactions of different types can be recorded over time. And, a number of recent works have shown that this information can be used to build richer individual user models and to discover additional behavioral patterns that can be leveraged in the recommendation process. In this work we review existing works that consider information from such sequentially-ordered user- item interaction logs in the recommendation process. Based on this review, we propose a categorization of the corresponding recommendation tasks and goals, summarize existing algorithmic solutions, discuss methodological approaches when benchmarking what we call sequence-aware recommender systems, and outline open challenges in the area.}, note = {Pre SFI}, keywords = {Collaborative filtering, Computing Methodology, Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {article} } Recommender systems are one of the most successful applications of data mining and machine learning technology in practice. Academic research in the field is historically often based on the matrix completion problem formulation, where for each user-item-pair only one interaction (e.g., a rating) is considered. In many application domains, however, multiple user-item interactions of different types can be recorded over time. And, a number of recent works have shown that this information can be used to build richer individual user models and to discover additional behavioral patterns that can be leveraged in the recommendation process. In this work we review existing works that consider information from such sequentially-ordered user- item interaction logs in the recommendation process. Based on this review, we propose a categorization of the corresponding recommendation tasks and goals, summarize existing algorithmic solutions, discuss methodological approaches when benchmarking what we call sequence-aware recommender systems, and outline open challenges in the area. |
| Ad Hoc Table Retrieval using Semantic Similarity Conference Shuo Zhang; Krisztian Balog Proceedings of The Web Conference 2018 (WWW’18), 2018, (Pre SFI). Abstract | BibTeX | Tags: Semantic matching, Semantic representations, Semantic similarity, Table retrieval, Table search, WP2: User Modeling Personalization and Engagement | Links: @conference{Zhang2018, title = {Ad Hoc Table Retrieval using Semantic Similarity}, author = {Shuo Zhang and Krisztian Balog}, url = {https://arxiv.org/pdf/1802.06159.pdf}, doi = {10.1145/3178876.3186067}, year = {2018}, date = {2018-02-16}, booktitle = {Proceedings of The Web Conference 2018 (WWW’18)}, pages = {1553-1562}, abstract = {We introduce and address the problem of ad hoc table retrieval: answering a keyword query with a ranked list of tables. This task is not only interesting on its own account, but is also being used as a core component in many other table-based information access scenarios, such as table completion or table mining. The main novel contribution of this work is a method for performing semantic matching between queries and tables. Specifically, we (i) represent queries and tables in multiple semantic spaces (both discrete sparse and continuous dense vector representations) and (ii) introduce various similarity measures for matching those semantic representations. We consider all possible combinations of semantic representations and similarity measures and use these as features in a supervised learning model. Using a purpose-built test collection based on Wikipedia tables, we demonstrate significant and substantial improvements over a state-of-the-art baseline.}, note = {Pre SFI}, keywords = {Semantic matching, Semantic representations, Semantic similarity, Table retrieval, Table search, WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {conference} } We introduce and address the problem of ad hoc table retrieval: answering a keyword query with a ranked list of tables. This task is not only interesting on its own account, but is also being used as a core component in many other table-based information access scenarios, such as table completion or table mining. The main novel contribution of this work is a method for performing semantic matching between queries and tables. Specifically, we (i) represent queries and tables in multiple semantic spaces (both discrete sparse and continuous dense vector representations) and (ii) introduce various similarity measures for matching those semantic representations. We consider all possible combinations of semantic representations and similarity measures and use these as features in a supervised learning model. Using a purpose-built test collection based on Wikipedia tables, we demonstrate significant and substantial improvements over a state-of-the-art baseline. |
| The Future of Audiences: A Foresight Analysis of Interfaces and Engagement Book Ranjana Das; Brita Ytre-Arne (Ed.) 1st, Palgrave Macmillan, 2018, ISBN: 978-3-319-75637-0, (Pre SFI). Abstract | BibTeX | Tags: WP1: Understanding Media Experiences | Links: @book{Das2018, title = {The Future of Audiences: A Foresight Analysis of Interfaces and Engagement}, editor = {Ranjana Das and Brita Ytre-Arne}, url = {https://www.palgrave.com/gp/book/9783319756370#aboutBook}, doi = {10.1007/978-3-319-75638-7}, isbn = {978-3-319-75637-0}, year = {2018}, date = {2018-01-01}, publisher = {Palgrave Macmillan}, edition = {1st}, abstract = {This book brings together contributions from scholars across Europe to present findings from a foresight analysis exercise on audiences and audience analysis, looking towards an increasingly datafied world and anticipating the ubiquity of the internet of things. The book uses knowledge emerging out of three foresight exercises, produced in co-operation with more than 50 stake-holding organisations and building on systematic reviews of audience research. It works through these exercises to arrive at a renewed agenda for audience studies within communication scholarship in the context of intrusive and connected interfaces and emerging communicative practices. }, note = {Pre SFI}, keywords = {WP1: Understanding Media Experiences}, pubstate = {published}, tppubtype = {book} } This book brings together contributions from scholars across Europe to present findings from a foresight analysis exercise on audiences and audience analysis, looking towards an increasingly datafied world and anticipating the ubiquity of the internet of things. The book uses knowledge emerging out of three foresight exercises, produced in co-operation with more than 50 stake-holding organisations and building on systematic reviews of audience research. It works through these exercises to arrive at a renewed agenda for audience studies within communication scholarship in the context of intrusive and connected interfaces and emerging communicative practices. |
| Entity-Oriented Search Book Krisztian Balog 1, Springer, 2018, ISBN: 978-3-319-93935-3, (Pre SFI). Abstract | BibTeX | Tags: WP2: User Modeling Personalization and Engagement | Links: @book{Balog2018, title = {Entity-Oriented Search}, author = {Krisztian Balog}, url = {https://www.springer.com/gp/book/9783319939339}, doi = {10.1007/978-3-319-93935-3}, isbn = {978-3-319-93935-3}, year = {2018}, date = {2018-01-01}, volume = {39}, publisher = {Springer}, edition = {1}, abstract = {This open access book covers all facets of entity-oriented search—where “search” can be interpreted in the broadest sense of information access—from a unified point of view, and provides a coherent and comprehensive overview of the state of the art. It represents the first synthesis of research in this broad and rapidly developing area. Selected topics are discussed in-depth, the goal being to establish fundamental techniques and methods as a basis for future research and development. Additional topics are treated at a survey level only, containing numerous pointers to the relevant literature. A roadmap for future research, based on open issues and challenges identified along the way, rounds out the book.}, note = {Pre SFI}, keywords = {WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {book} } This open access book covers all facets of entity-oriented search—where “search” can be interpreted in the broadest sense of information access—from a unified point of view, and provides a coherent and comprehensive overview of the state of the art. It represents the first synthesis of research in this broad and rapidly developing area. Selected topics are discussed in-depth, the goal being to establish fundamental techniques and methods as a basis for future research and development. Additional topics are treated at a survey level only, containing numerous pointers to the relevant literature. A roadmap for future research, based on open issues and challenges identified along the way, rounds out the book. |
| Multi-device Linear Composition on the Web, Enabling Multi-device Linear Media with HTMLTimingObject and Shared Motion Conference Ingar Mæhlum Arntzen; Njål Borch; François Daoust; Dominique Hazael-Massieux Media Synchronization Workshop Brussels, 2018, (Pre SFI). Abstract | BibTeX | Tags: Linear Media, Multi-device, Shared Motion, WP4: Media Content Interaction and Accessibility | Links: @conference{Arntzen2018b, title = {Multi-device Linear Composition on the Web, Enabling Multi-device Linear Media with HTMLTimingObject and Shared Motion}, author = {Ingar Mæhlum Arntzen and Njål Borch and François Daoust and Dominique Hazael-Massieux }, url = {https://www.researchgate.net/publication/324991987_Multi-device_Linear_Composition_on_the_Web_Enabling_Multi-device_Linear_Media_with_HTMLTimingObject_and_Shared_Motion}, year = {2018}, date = {2018-01-01}, address = {Brussels}, organization = {Media Synchronization Workshop}, abstract = {Composition is a hallmark of the Web, yet it does not fully extend to linear media. This paper defines linear composition as the ability to form linear media by coordinated playback of independent linear components. We argue that native Web support for linear composition is a key enabler for Web-based multi-device linear media, and that precise multi-device timing is the main technical challenge. This paper proposes the introduction of an HTMLTimingObject as basis for linear composition in the single-device scenario. Linear composition in the multi-device scenario is ensured as HTMLTimingObjects may integrate with Shared Motion, a generic timing mechanism for the Web. By connecting HTMLMediaElements and HTMLTrackElements with a multi-device timing mechanism, a powerful programming model for multi-device linear media is unlocked.}, note = {Pre SFI}, keywords = {Linear Media, Multi-device, Shared Motion, WP4: Media Content Interaction and Accessibility}, pubstate = {published}, tppubtype = {conference} } Composition is a hallmark of the Web, yet it does not fully extend to linear media. This paper defines linear composition as the ability to form linear media by coordinated playback of independent linear components. We argue that native Web support for linear composition is a key enabler for Web-based multi-device linear media, and that precise multi-device timing is the main technical challenge. This paper proposes the introduction of an HTMLTimingObject as basis for linear composition in the single-device scenario. Linear composition in the multi-device scenario is ensured as HTMLTimingObjects may integrate with Shared Motion, a generic timing mechanism for the Web. By connecting HTMLMediaElements and HTMLTrackElements with a multi-device timing mechanism, a powerful programming model for multi-device linear media is unlocked. |
| The Roadmap to User-Controllable Social Exploratory Search Journal Article Cecilia Di Sciascio; Peter Brusilovsky; Christoph Trattner; Eduardo Veas ACM Transactions on Interactive Intelligent Systems, pp. 1-37, 2018, (Pre SFI). Abstract | BibTeX | Tags: CCS Concepts, Computer systems organization, Embedded systems, Network reliability;, Networks, Redundancy, Robotics | Links: @article{Sciascio2018, title = {The Roadmap to User-Controllable Social Exploratory Search}, author = {Cecilia Di Sciascio and Peter Brusilovsky and Christoph Trattner and Eduardo Veas}, url = {https://www.christophtrattner.info/pubs/TIIS2019.pdf}, year = {2018}, date = {2018-01-01}, journal = {ACM Transactions on Interactive Intelligent Systems}, pages = {1-37}, abstract = {Information-seeking tasks with learning or investigative purposes are usually referred to as exploratory search. Exploratory search unfolds as a dynamic process where the user, amidst navigation, trial-and-error and on-the-!y selections, gathers and organizes information (resources). A range of innovative interfaces with increased user control have been developed to support exploratory search process. In this work we present our attempt to increase the power of exploratory search interfaces by using ideas of social search, i.e., leveraging information left by past users of information systems. Social search technologies are highly popular nowadays, especially for improving ranking. However, current approaches to social ranking do not allow users to decide to what extent social information should be taken into account for result ranking. This paper presents an interface that integrates social search functionality into an exploratory search system in a user-controlled way that is consistent with the nature of exploratory search. The interface incorporates control features that allow the user to (i) express information needs by selecting keywords and (ii) to express preferences for incorporating social wisdom based on tag matching and user similarity. The interface promotes search transparency through color-coded stacked bars and rich tooltips. This work presents the full series of evaluations conducted to, "rst, assess the value of the social models in contexts independent to the user interface, in terms of objective and perceived accuracy. Then, in a study with the full-!edged system, we investigated system accuracy and subjective aspects with a structural model that revealed that, when users actively interacted with all its control features, the hybrid system outperformed a baseline content-based-only tool and users were more satis"ed.}, note = {Pre SFI}, keywords = {CCS Concepts, Computer systems organization, Embedded systems, Network reliability;, Networks, Redundancy, Robotics}, pubstate = {published}, tppubtype = {article} } Information-seeking tasks with learning or investigative purposes are usually referred to as exploratory search. Exploratory search unfolds as a dynamic process where the user, amidst navigation, trial-and-error and on-the-!y selections, gathers and organizes information (resources). A range of innovative interfaces with increased user control have been developed to support exploratory search process. In this work we present our attempt to increase the power of exploratory search interfaces by using ideas of social search, i.e., leveraging information left by past users of information systems. Social search technologies are highly popular nowadays, especially for improving ranking. However, current approaches to social ranking do not allow users to decide to what extent social information should be taken into account for result ranking. This paper presents an interface that integrates social search functionality into an exploratory search system in a user-controlled way that is consistent with the nature of exploratory search. The interface incorporates control features that allow the user to (i) express information needs by selecting keywords and (ii) to express preferences for incorporating social wisdom based on tag matching and user similarity. The interface promotes search transparency through color-coded stacked bars and rich tooltips. This work presents the full series of evaluations conducted to, "rst, assess the value of the social models in contexts independent to the user interface, in terms of objective and perceived accuracy. Then, in a study with the full-!edged system, we investigated system accuracy and subjective aspects with a structural model that revealed that, when users actively interacted with all its control features, the hybrid system outperformed a baseline content-based-only tool and users were more satis"ed. |
| Hierarchy of influences on transitional journalism–Corrupting relationships between political, economic and media elites Journal Article Ana Milojevic; Aleksandra Krstić European Journal of Communication, 33 (1), pp. 37-56, 2018, (Pre SFI). Abstract | BibTeX | Tags: Corruption, hierarchy-of-influences, media autonomy, Serbia, transitional journalism, WP1: Understanding Media Experiences | Links: @article{Milojevic2018, title = {Hierarchy of influences on transitional journalism–Corrupting relationships between political, economic and media elites}, author = {Ana Milojevic and Aleksandra Krstić}, url = {https://www.researchgate.net/publication/322260163_Hierarchy_of_influences_on_transitional_journalism_-_Corrupting_relationships_between_political_economic_and_media_elites}, year = {2018}, date = {2018-01-01}, journal = {European Journal of Communication}, volume = {33}, number = {1}, pages = {37-56}, abstract = {In this article, we use the hierarchy-of-influences model as a framework for examining the ways in which media owners, managers and journalists perceive the influence exerted on their work during 12-year democratic transition in Serbia. We aim to explain how factors perceived as influential at the highest system level gradually transfer and relate to the factors on the subsumed levels. Using the concepts such as corruption and the culture of corruption to interpret hierarchy between different levels of influence on transitional journalism, we argue that coupling extra-media actors at the system level can be considered corruption – understood as abuse of power for personal gain or benefit of the aligned group – which translates to all other levels of influence.}, note = {Pre SFI}, keywords = {Corruption, hierarchy-of-influences, media autonomy, Serbia, transitional journalism, WP1: Understanding Media Experiences}, pubstate = {published}, tppubtype = {article} } In this article, we use the hierarchy-of-influences model as a framework for examining the ways in which media owners, managers and journalists perceive the influence exerted on their work during 12-year democratic transition in Serbia. We aim to explain how factors perceived as influential at the highest system level gradually transfer and relate to the factors on the subsumed levels. Using the concepts such as corruption and the culture of corruption to interpret hierarchy between different levels of influence on transitional journalism, we argue that coupling extra-media actors at the system level can be considered corruption – understood as abuse of power for personal gain or benefit of the aligned group – which translates to all other levels of influence. |
2017 |
| Valgkampens store tabu Online Torstein Harildstad Dagbladet 2017, (Pre SFI). BibTeX | Tags: Debatt, Digitalisering | Links: @online{Harildstad2017, title = {Valgkampens store tabu}, author = {Torstein Harildstad}, url = {https://www.dagbladet.no/kultur/valgkampens-store-tabu/68665330}, year = {2017}, date = {2017-09-07}, organization = {Dagbladet}, note = {Pre SFI}, keywords = {Debatt, Digitalisering}, pubstate = {published}, tppubtype = {online} } |
| Verifying information with multimedia content on twitter: A comparative study of automated approaches Journal Article Christina Boididou; Stuart Middleton; Zhiwei Jin; Symeon Papadopoulos; Duc-Tien Dang Nguyen; G. Boato; Ioannis (Yiannis) Kompatsiaris Multimedia Tools and Applications, 77 (12), pp. 15545-15571, 2017, (Pre SFI). Abstract | BibTeX | Tags: Credibility, Fake Detection, Multimedia, Social Media, Trust, Twitter, Veracity, Verification, WP3: Media Content Production and Analysis | Links: @article{Boididou2017, title = {Verifying information with multimedia content on twitter: A comparative study of automated approaches}, author = {Christina Boididou and Stuart Middleton and Zhiwei Jin and Symeon Papadopoulos and Duc-Tien Dang Nguyen and G. Boato and Ioannis (Yiannis) Kompatsiaris}, url = {https://www.researchgate.net/publication/319859894_Verifying_information_with_multimedia_content_on_twitter_A_comparative_study_of_automated_approaches}, doi = {10.1007/s11042-017-5132-9}, year = {2017}, date = {2017-09-01}, journal = {Multimedia Tools and Applications}, volume = {77}, number = {12}, pages = {15545-15571}, abstract = {An increasing amount of posts on social media are used for dissem- inating news information and are accompanied by multimedia content. Such content may often be misleading or be digitally manipulated. More often than not, such pieces of content reach the front pages of major news outlets, having a detrimental eect on their credibility. To avoid such eects, there is profound need for automated methods that can help debunk and verify online content in very short time. To this end, we present a comparative study of three such methods that are catered for Twitter, a major social media platform used for news sharing. Those include: a) a method that uses textual patterns to extract }, note = {Pre SFI}, keywords = {Credibility, Fake Detection, Multimedia, Social Media, Trust, Twitter, Veracity, Verification, WP3: Media Content Production and Analysis}, pubstate = {published}, tppubtype = {article} } An increasing amount of posts on social media are used for dissem- inating news information and are accompanied by multimedia content. Such content may often be misleading or be digitally manipulated. More often than not, such pieces of content reach the front pages of major news outlets, having a detrimental eect on their credibility. To avoid such eects, there is profound need for automated methods that can help debunk and verify online content in very short time. To this end, we present a comparative study of three such methods that are catered for Twitter, a major social media platform used for news sharing. Those include: a) a method that uses textual patterns to extract |
| Effective User Interface Designs to Increase Energy-efficient Behavior in a Rasch-based Energy Recommender System Conference Alain D. Starke; Martijn C. Willemsen; Chris C.P. Snijders (August 2017), 2017. Abstract | BibTeX | Tags: Applied computing, Human-centered computing, Information Systems | Links: @conference{Starke2017, title = {Effective User Interface Designs to Increase Energy-efficient Behavior in a Rasch-based Energy Recommender System}, author = {Alain D. Starke and Martijn C. Willemsen and Chris C.P. Snijders}, url = {https://dl.acm.org/doi/abs/10.1145/3109859.3109902}, doi = {10.1145/3109859.3109902}, year = {2017}, date = {2017-08-27}, number = {August 2017}, pages = {1-9}, abstract = {People often struggle to find appropriate energy-saving measures to take in the household. Although recommender studies show that tailoring a system's interaction method to the domain knowledge of the user can increase energy savings, they did not actually tailor the conservation advice itself. We present two large user studies in which we support users to make an energy-efficient behavioral change by presenting tailored energy-saving advice. Both systems use a one-dimensional, ordinal Rasch scale, which orders 79 energy-saving measures on their behavioral difficulty and link this to a user's energy-saving ability for tailored advice. We established that recommending Rasch-based advice can reduce a user's effort, increase system support and, in turn, increase choice satisfaction and lead to the adoption of more energy-saving measures. Moreover, follow-up surveys administered four weeks later point out that tailoring advice on its feasibility can support behavioral change.}, keywords = {Applied computing, Human-centered computing, Information Systems}, pubstate = {published}, tppubtype = {conference} } People often struggle to find appropriate energy-saving measures to take in the household. Although recommender studies show that tailoring a system's interaction method to the domain knowledge of the user can increase energy savings, they did not actually tailor the conservation advice itself. We present two large user studies in which we support users to make an energy-efficient behavioral change by presenting tailored energy-saving advice. Both systems use a one-dimensional, ordinal Rasch scale, which orders 79 energy-saving measures on their behavioral difficulty and link this to a user's energy-saving ability for tailored advice. We established that recommending Rasch-based advice can reduce a user's effort, increase system support and, in turn, increase choice satisfaction and lead to the adoption of more energy-saving measures. Moreover, follow-up surveys administered four weeks later point out that tailoring advice on its feasibility can support behavioral change. |
| Økt samvirke og beslutningsstøtte – Case Salten Brann IKS Technical Report Njål Borch 2017, (Pre SFI). BibTeX | Tags: WP4: Media Content Interaction and Accessibility | Links: @techreport{Borch2017, title = {Økt samvirke og beslutningsstøtte – Case Salten Brann IKS}, author = {Njål Borch}, url = {https://norceresearch.brage.unit.no/norceresearch-xmlui/handle/11250/2647818}, year = {2017}, date = {2017-08-17}, note = {Pre SFI}, keywords = {WP4: Media Content Interaction and Accessibility}, pubstate = {published}, tppubtype = {techreport} } |
| Exploring the semantic gap for movie recommendations Conference Mehdi Elahi; Yashar Deldjoo; Farshad Bakhshandegan Moghaddam; Leonardo Cella; Stefano Cerada; Paolo Cremonesi Proceedings of the Eleventh ACM Conference on Recommender Systems, Association for Computing Machinery New York, 2017, (Pre SFI). Abstract | BibTeX | Tags: Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement | Links: @conference{Elahi2017, title = {Exploring the semantic gap for movie recommendations}, author = {Mehdi Elahi and Yashar Deldjoo and Farshad Bakhshandegan Moghaddam and Leonardo Cella and Stefano Cerada and Paolo Cremonesi }, url = {https://dl.acm.org/doi/pdf/10.1145/3109859.3109908}, doi = {https://doi.org/10.1145/3109859.3109908}, year = {2017}, date = {2017-08-01}, booktitle = {Proceedings of the Eleventh ACM Conference on Recommender Systems}, pages = {326–330}, address = {New York}, organization = {Association for Computing Machinery}, abstract = {In the last years, there has been much attention given to the semantic gap problem in multimedia retrieval systems. Much effort has been devoted to bridge this gap by building tools for the extraction of high-level, semantics-based features from multimedia content, as low-level features are not considered useful because they deal primarily with representing the perceived content rather than the semantics of it. In this paper, we explore a different point of view by leveraging the gap between low-level and high-level features. We experiment with a recent approach for movie recommendation that extract low-level Mise-en-Scéne features from multimedia content and combine it with high-level features provided by the wisdom of the crowd. To this end, we first performed an offline performance assessment by implementing a pure content-based recommender system with three different versions of the same algorithm, respectively based on (i) conventional movie attributes, (ii) mise-en-scene features, and (iii) a hybrid method that interleaves recommendations based on movie attributes and mise-en-scene features. In a second study, we designed an empirical study involving 100 subjects and collected data regarding the quality perceived by the users. Results from both studies show that the introduction of mise-en-scéne features in conjunction with traditional movie attributes improves both offline and online quality of recommendations.}, note = {Pre SFI}, keywords = {Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement}, pubstate = {published}, tppubtype = {conference} } In the last years, there has been much attention given to the semantic gap problem in multimedia retrieval systems. Much effort has been devoted to bridge this gap by building tools for the extraction of high-level, semantics-based features from multimedia content, as low-level features are not considered useful because they deal primarily with representing the perceived content rather than the semantics of it. In this paper, we explore a different point of view by leveraging the gap between low-level and high-level features. We experiment with a recent approach for movie recommendation that extract low-level Mise-en-Scéne features from multimedia content and combine it with high-level features provided by the wisdom of the crowd. To this end, we first performed an offline performance assessment by implementing a pure content-based recommender system with three different versions of the same algorithm, respectively based on (i) conventional movie attributes, (ii) mise-en-scene features, and (iii) a hybrid method that interleaves recommendations based on movie attributes and mise-en-scene features. In a second study, we designed an empirical study involving 100 subjects and collected data regarding the quality perceived by the users. Results from both studies show that the introduction of mise-en-scéne features in conjunction with traditional movie attributes improves both offline and online quality of recommendations. |
| Multimodal Retrieval with Diversification and Relevance Feedback for Tourist Attraction Images Journal Article Duc-Tien Dang Nguyen; Luca Piras; Giorgio Giacinto; G. Boato; Francesco G. B. DE Natale 14 (4), pp. 1-24, 2017, (Pre SFI). Abstract | BibTeX | Tags: WP3: Media Content Production and Analysis | Links: @article{Nguyen2017, title = {Multimodal Retrieval with Diversification and Relevance Feedback for Tourist Attraction Images}, author = {Duc-Tien Dang Nguyen and Luca Piras and Giorgio Giacinto and G. Boato and Francesco G. B. DE Natale }, url = {https://www.researchgate.net/publication/319114515_Multimodal_Retrieval_with_Diversification_and_Relevance_Feedback_for_Tourist_Attraction_Images}, doi = {10.1145/3103613}, year = {2017}, date = {2017-08-01}, booktitle = {ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)}, volume = {14}, number = {4}, pages = {1-24}, abstract = {In this article, we present a novel framework that can produce a visual description of a tourist attraction by choosing the most diverse pictures from community-contributed datasets, which describe different details of the queried location. The main strength of the proposed approach is its flexibility that permits us to filter out non-relevant images and to obtain a reliable set of diverse and relevant images by first clustering similar images according to their textual descriptions and their visual content and then extracting images from different clusters according to a measure of the user’s credibility. Clustering is based on a two-step process, where textual descriptions are used first and the clusters are then refined according to the visual features. The degree of diversification can be further increased by exploiting users’ judgments on the results produced by the proposed algorithm through a novel approach, where users not only provide a relevance feedback but also a diversity feedback. Experimental results performed on the MediaEval 2015 “Retrieving Diverse Social Images” dataset show that the proposed framework can achieve very good performance both in the case of automatic retrieval of diverse images and in the case of the exploitation of the users’ feedback. The effectiveness of the proposed approach has been also confirmed by a small case study involving a number of real users.}, note = {Pre SFI}, keywords = {WP3: Media Content Production and Analysis}, pubstate = {published}, tppubtype = {article} } In this article, we present a novel framework that can produce a visual description of a tourist attraction by choosing the most diverse pictures from community-contributed datasets, which describe different details of the queried location. The main strength of the proposed approach is its flexibility that permits us to filter out non-relevant images and to obtain a reliable set of diverse and relevant images by first clustering similar images according to their textual descriptions and their visual content and then extracting images from different clusters according to a measure of the user’s credibility. Clustering is based on a two-step process, where textual descriptions are used first and the clusters are then refined according to the visual features. The degree of diversification can be further increased by exploiting users’ judgments on the results produced by the proposed algorithm through a novel approach, where users not only provide a relevance feedback but also a diversity feedback. Experimental results performed on the MediaEval 2015 “Retrieving Diverse Social Images” dataset show that the proposed framework can achieve very good performance both in the case of automatic retrieval of diverse images and in the case of the exploitation of the users’ feedback. The effectiveness of the proposed approach has been also confirmed by a small case study involving a number of real users. |
| Exploiting Food Choice Biases for Healthier Recipe Recommendation Conference David Elsweiler; Christoph Trattner; Morgan Harvey ACM SIGIR Conference 2017, (Pre SFI). Abstract | BibTeX | Tags: Behavioural change, Food RecSys, Human decision making, Information behaviour | Links: @conference{Elsweiler2017, title = {Exploiting Food Choice Biases for Healthier Recipe Recommendation}, author = {David Elsweiler and Christoph Trattner and Morgan Harvey}, url = {https://www.christophtrattner.info/pubs/SIGIR2017.pdf}, year = {2017}, date = {2017-08-01}, organization = {ACM SIGIR Conference}, abstract = {By incorporating healthiness into the food recommendation / ranking process we have the potential to improve the eating habits of a growing number of people who use the Internet as a source of food inspiration. In this paper, using insights gained from various data sources, we explore the feasibility of substituting meals that would typically be recommended to users with similar, healthier dishes. First, by analysing a recipe collection sourced from Allrecipes.com, we quantify the potential for nding replacement recipes, which are comparable but have di erent nutritional characteristics and are nevertheless highly rated by users. Building on this, we present two controlled user studies (n=107, n=111) investigating how people perceive and select recipes. We show participants are unable to reliably identify which recipe contains most fat due to their answers being biased by lack of information, misleading cues and limited nutritional knowledge on their part. By applying machine learning techniques to predict the preferred recipes, good performance can be achieved using low-level image features and recipe meta-data as predictors. Despite not being able to consciously determine which of two recipes contains most fat, on average, participants select the recipe with the most fat as their preference. The importance of image features reveals that recipe choices are often visually driven. A nal user study (n=138) investigates to what extent the predictive models can be used to select recipe replacements such that users can be “nudged” towards choosing healthier recipes. Our ndings have important implications for online food systems.}, note = {Pre SFI}, keywords = {Behavioural change, Food RecSys, Human decision making, Information behaviour}, pubstate = {published}, tppubtype = {conference} } By incorporating healthiness into the food recommendation / ranking process we have the potential to improve the eating habits of a growing number of people who use the Internet as a source of food inspiration. In this paper, using insights gained from various data sources, we explore the feasibility of substituting meals that would typically be recommended to users with similar, healthier dishes. First, by analysing a recipe collection sourced from Allrecipes.com, we quantify the potential for nding replacement recipes, which are comparable but have di erent nutritional characteristics and are nevertheless highly rated by users. Building on this, we present two controlled user studies (n=107, n=111) investigating how people perceive and select recipes. We show participants are unable to reliably identify which recipe contains most fat due to their answers being biased by lack of information, misleading cues and limited nutritional knowledge on their part. By applying machine learning techniques to predict the preferred recipes, good performance can be achieved using low-level image features and recipe meta-data as predictors. Despite not being able to consciously determine which of two recipes contains most fat, on average, participants select the recipe with the most fat as their preference. The importance of image features reveals that recipe choices are often visually driven. A nal user study (n=138) investigates to what extent the predictive models can be used to select recipe replacements such that users can be “nudged” towards choosing healthier recipes. Our ndings have important implications for online food systems. |