Please use this identifier to cite or link to this item: https://oa.tib.eu/renate/handle/123456789/11633
Files in This Item:
File SizeFormat 
Towards_Analyzing_the_Bias.pdf666,46 kBAdobe PDFView/Open
Title: Towards Analyzing the Bias of News Recommender Systems Using Sentiment and Stance Detection
Authors: Alam, MehwishIana, AndreeaGrote, AlexanderLudwig, KatharinaMüller, PhilippPaulheim, Heiko
Editors: Laforest, FrédériqueTroncy, RaphaelMédini, LionelHerman, Ivan
Publishers version: https://doi.org/10.1145/3487553.3524674
URI: https://oa.tib.eu/renate/handle/123456789/11633
http://dx.doi.org/10.34657/10666
Issue Date: 2022
Published in: ACM Digital Library
Book: Companion Proceedings of the Web Conference 2022
Journal: ACM Digital Library
Page Start: 448
Page End: 457
Publisher: New York,NY,United States : Association for Computing Machinery
Abstract: News recommender systems are used by online news providers to alleviate information overload and to provide personalized content to users. However, algorithmic news curation has been hypothesized to create filter bubbles and to intensify users' selective exposure, potentially increasing their vulnerability to polarized opinions and fake news. In this paper, we show how information on news items' stance and sentiment can be utilized to analyze and quantify the extent to which recommender systems suffer from biases. To that end, we have annotated a German news corpus on the topic of migration using stance detection and sentiment analysis. In an experimental evaluation with four different recommender systems, our results show a slight tendency of all four models for recommending articles with negative sentiments and stances against the topic of refugees and migration. Moreover, we observed a positive correlation between the sentiment and stance bias of the text-based recommenders and the preexisting user bias, which indicates that these systems amplify users' opinions and decrease the diversity of recommended news. The knowledge-aware model appears to be the least prone to such biases, at the cost of predictive accuracy.
Keywords: echo chambers; filter bubbles; German news articles; news recommendation; polarization; sentiment analysis; stance detection; Konferenzschrift
Type: bookPart; Text
Publishing status: publishedVersion
DDC: 020
004
License: CC BY 4.0 Unported
Link to license: https://creativecommons.org/licenses/by/4.0/
Appears in Collections:Informatik
Informationswissenschaften

Show full item record
Alam, Mehwish, Andreea Iana, Alexander Grote, Katharina Ludwig, Philipp Müller and Heiko Paulheim, 2022. Towards Analyzing the Bias of News Recommender Systems Using Sentiment and Stance Detection. In: (Hrsg.)Frédérique Laforest, Raphael Troncy, Lionel Médini and Ivan Herman. New York,NY,United States : Association for Computing Machinery. ISBN 978-145039130-6
Alam, M., Iana, A., Grote, A., Ludwig, K., Müller, P. and Paulheim, H. (2022) “Towards Analyzing the Bias of News Recommender Systems Using Sentiment and Stance Detection.” New York,NY,United States : Association for Computing Machinery. doi: https://doi.org/10.1145/3487553.3524674.
Alam M, Iana A, Grote A, Ludwig K, Müller P, Paulheim H. Towards Analyzing the Bias of News Recommender Systems Using Sentiment and Stance Detection. In: , editorLaforest F, Troncy R, Médini L, Herman I. New York,NY,United States : Association for Computing Machinery; 2022.
Alam, M., Iana, A., Grote, A., Ludwig, K., Müller, P., & Paulheim, H. (2022). Towards Analyzing the Bias of News Recommender Systems Using Sentiment and Stance Detection. New York,NY,United States : Association for Computing Machinery. https://doi.org/https://doi.org/10.1145/3487553.3524674
Alam M, Iana A, Grote A, Ludwig K, Müller P, Paulheim H. Towards Analyzing the Bias of News Recommender Systems Using Sentiment and Stance Detection. In: , ed.Laforest F, Troncy R, Médini L, Herman I New York,NY,United States : Association for Computing Machinery; 2022. doi:https://doi.org/10.1145/3487553.3524674


This item is licensed under a Creative Commons License Creative Commons