Deep Learning to Encourage Citizen Involvement in Local Journalism Journal Article Forthcoming Bjørnar Tessem; Lars Nyre; Michel dos Santos Mesquita; Paul Mulholland Futures of Journalism. Palgrave Macmillan. , Forthcoming. BibTeX @article{dosMulholland2021,
title = {Deep Learning to Encourage Citizen Involvement in Local Journalism},
author = {Bjørnar Tessem and Lars Nyre and Michel dos Santos Mesquita and Paul Mulholland},
editor = {In Ville Manninen et al.},
year = {2021},
date = {2021-12-31},
journal = {Futures of Journalism. Palgrave Macmillan. },
keywords = {},
pubstate = {forthcoming},
tppubtype = {article}
}
|
The Cholesterol Factor: Balancing Accuracy and Health in Recipe Recommendation Through a Nutrient-Specific Metric. Proceeding Forthcoming Alain Starke; Christoph Trattner; H. Bakken; M. Johannessen; V. Solberg Forthcoming. BibTeX @proceedings{Starke2021bb,
title = {The Cholesterol Factor: Balancing Accuracy and Health in Recipe Recommendation Through a Nutrient-Specific Metric.},
author = {Alain Starke and Christoph Trattner and H. Bakken and M. Johannessen and V. Solberg},
year = {2021},
date = {2021-09-27},
journal = {Workshop on Multi-Objective Recommender Systems (MORS) held at RecSys'21. },
keywords = {},
pubstate = {forthcoming},
tppubtype = {proceedings}
}
|
| Predicting Feature-based Similarity in the News Domain Using Human Judgments. Proceeding Forthcoming Alain Starke; Sebastian Øverhaug Larsen; Christoph Trattner. International Workshop on News Recommendation and Analytics (INRA 2021) held at RecSys'21.September, 2021, Amsterdam, NL. ACM, New York, NY, USA., Forthcoming. Abstract | BibTeX | Links: @proceedings{Starke2021b,
title = {Predicting Feature-based Similarity in the News Domain Using Human Judgments. },
author = {Alain Starke and Sebastian Øverhaug Larsen and Christoph Trattner.},
url = {https://www.christophtrattner.info/pubs/NewsRecSys2021.pdf
https: //doi.org/10.1145/1122445.1122456},
year = {2021},
date = {2021-09-27},
journal = {9th International Workshop on News Recommendation and Analytics (INRA 2021) held at RecSys'21. 2021.},
publisher = {International Workshop on News Recommendation and Analytics (INRA 2021) held at RecSys'21.September, 2021, Amsterdam, NL. ACM, New York, NY, USA.},
abstract = {When reading an online news article, users are typically presented ‘more like this’ recommendations by news websites. In this study, we assessed different similarity functions for news item retrieval, by comparing them to human judgments of similarity. We asked 401 participants to assess the overall similarity of ten pairs of political news articles, which were compared to feature-specific similarity functions (e.g., based on body text or images). We found that users indicated to mostly use text-based features (e.g., title) for their similarity judgments, suggesting that body text similarity was the most representative for their judgment. Moreover, we modeled similarity judgments using different regression techniques. Using data from another study, we contrasted our results across retrieval domains, revealing that similarity functions in news are less representative of user judgments than those in movies and recipes.},
keywords = {},
pubstate = {forthcoming},
tppubtype = {proceedings}
}
When reading an online news article, users are typically presented ‘more like this’ recommendations by news websites. In this study, we assessed different similarity functions for news item retrieval, by comparing them to human judgments of similarity. We asked 401 participants to assess the overall similarity of ten pairs of political news articles, which were compared to feature-specific similarity functions (e.g., based on body text or images). We found that users indicated to mostly use text-based features (e.g., title) for their similarity judgments, suggesting that body text similarity was the most representative for their judgment. Moreover, we modeled similarity judgments using different regression techniques. Using data from another study, we contrasted our results across retrieval domains, revealing that similarity functions in news are less representative of user judgments than those in movies and recipes. |
| Recommending Videos in Cold Start With Automatic Visual Tags Proceeding Mehdi Elahi; Farshad B. Moghaddam; Reza Hosseini; Mohammad Hossein Rimaz; Nabil El Ioini; Marko Tkalcic; Christoph Trattner; Tammam Tillo 29th Conference on User Modeling, Adaptation and Personalization conference (UMAP 2021) Utrecht, the Netherlands, 2021. Abstract | BibTeX | Links: @proceedings{Elahi2021,
title = {Recommending Videos in Cold Start With Automatic Visual Tags},
author = {Mehdi Elahi and Farshad B. Moghaddam and Reza Hosseini and Mohammad Hossein Rimaz and Nabil El Ioini and Marko Tkalcic and Christoph Trattner and Tammam Tillo },
url = {https://www.researchgate.net/publication/351696161_Recommending_Videos_in_Cold_Start_With_Automatic_Visual_Tags
},
doi = {10.1145/3450614.3461687},
year = {2021},
date = {2021-07-01},
address = {Utrecht, the Netherlands},
organization = {29th Conference on User Modeling, Adaptation and Personalization conference (UMAP 2021)},
abstract = {Preprint and dataset available! This paper addresses the so-called New Item problem in video Recommender Systems, as part of Cold Start. New item problem occurs when a new item is added to the system catalog, and the recommender system has no or little data describing that item. This could cause the system to fail to meaningfully recommend the new item to the users. We propose a novel technique that can generate cold start recommendation by utilizing automatic visual tags, i.e., tags that are automatically annotated by deeply analyzing the content of the videos and detecting faces, objects, and even celebrities within the videos. The automatic visual tags do not need any human involvement and have been shown to be very effective in representing the video content. In order to evaluate our proposed technique, we have performed a set of experiments using a large dataset of videos. The results have shown that the automatically extracted visual tags can be incorporated into the cold start recommendation process and achieve superior results compared to the recommendation based on human-annotated tags.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Preprint and dataset available! This paper addresses the so-called New Item problem in video Recommender Systems, as part of Cold Start. New item problem occurs when a new item is added to the system catalog, and the recommender system has no or little data describing that item. This could cause the system to fail to meaningfully recommend the new item to the users. We propose a novel technique that can generate cold start recommendation by utilizing automatic visual tags, i.e., tags that are automatically annotated by deeply analyzing the content of the videos and detecting faces, objects, and even celebrities within the videos. The automatic visual tags do not need any human involvement and have been shown to be very effective in representing the video content. In order to evaluate our proposed technique, we have performed a set of experiments using a large dataset of videos. The results have shown that the automatically extracted visual tags can be incorporated into the cold start recommendation process and achieve superior results compared to the recommendation based on human-annotated tags. |
| Exploring the Effects of Natural Language Justifications in Food Recommender Systems Proceeding Cataldo Musto; Alain D. Starke; Christoph Trattner; Amon Rapp; Giovanni Semeraro
Association for Computing Machinery, New York, NY United States, 2021, ISBN: 978-1-4503-8366-0. BibTeX | Links: @proceedings{Semeraro2021,
title = {Exploring the Effects of Natural Language Justifications in Food Recommender Systems},
author = {Cataldo Musto and Alain D. Starke and Christoph Trattner and Amon Rapp and Giovanni Semeraro
},
editor = {Judith Masthoff; Eelco Herder; Nava Tintarev; Marko Tkalčič},
doi = {https://doi.org/10.1145/3450613.3456827},
isbn = {978-1-4503-8366-0},
year = {2021},
date = {2021-06-21},
booktitle = {UMAP '21: 29th ACM Conference on User Modeling, Adaptation and Personalization },
pages = {147–157},
publisher = {Association for Computing Machinery},
address = {New York, NY United States},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
|
| Beyond Algorithmic Fairness in Recommender Systems Proceeding Mehdi Elahi; Himan Abdollahpouri; Masoud Mansoury; Helma Torkamaan Association for Computing Machinery, New York, NY United States, 2021, ISBN: 978-1-4503-8366-0. BibTeX | Links: @proceedings{Torkamaan2021,
title = {Beyond Algorithmic Fairness in Recommender Systems},
author = {Mehdi Elahi and Himan Abdollahpouri and Masoud Mansoury and Helma Torkamaan},
editor = {Judith Masthoff; Eelco Herder; Nava Tintarev; Marko Tkalčič},
doi = {https://doi.org/10.1145/3450614.3461685},
isbn = {978-1-4503-8366-0},
year = {2021},
date = {2021-06-21},
publisher = {Association for Computing Machinery},
address = {New York, NY United States},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
|
