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.
- Christian Baden and Nina Springer. 2017. Conceptualizing viewpoint diversity in news discourse. Journalism 18, 2 (2017), 176–194.Google ScholarCross Ref
- Eytan Bakshy, Solomon Messing, and Lada A Adamic. 2015. Exposure to ideologically diverse news and opinion on Facebook. Science 348, 6239 (2015), 1130–1132.Google Scholar
- Andrei Boutyline and Robb Willer. 2017. The social structure of political echo chambers: Variation in ideological homophily in online networks. Political psychology 38, 3 (2017), 551–569.Google Scholar
- Branden Chan, Stefan Schweter, and Timo Möller. 2020. German’s Next Language Model. In Proceedings of the 28th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Barcelona, Spain (Online), 6788–6796. https://doi.org/10.18653/v1/2020.coling-main.598Google ScholarCross Ref
- Alessandra Teresa Cignarella, Mirko Lai, Cristina Bosco, Viviana Patti, and Paolo Rosso. 2020. SardiStance @ EVALITA2020: Overview of the Task on Stance Detection in Italian Tweets. In Proceedings of the Seventh Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2020), Online event, December 17th, 2020(CEUR Workshop Proceedings, Vol. 2765). CEUR-WS.org. http://ceur-ws.org/Vol-2765/paper159.pdfGoogle Scholar
- Costanza Conforti, Jakob Berndt, Mohammad Taher Pilehvar, Chryssi Giannitsarou, Flavio Toxvaerd, and Nigel Collier. 2020. Will-They-Won’t-They: A Very Large Dataset for Stance Detection on Twitter. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel R. Tetreault (Eds.). Association for Computational Linguistics, 1715–1724. https://doi.org/10.18653/v1/2020.acl-main.157Google ScholarCross Ref
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), Jill Burstein, Christy Doran, and Thamar Solorio (Eds.). Association for Computational Linguistics, 4171–4186. https://doi.org/10.18653/v1/n19-1423Google Scholar
- Wolfgang Donsbach and Cornelia Mothes. 2013. The dissonant self: Contributions from dissonance theory to a new agenda for studying political communication. Annals of the International Communication Association 36, 1(2013), 3–44.Google ScholarCross Ref
- Michael Färber, Victoria Burkard, Adam Jatowt, and Sora Lim. 2020. A multidimensional dataset based on crowdsourcing for analyzing and detecting news bias. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 3007–3014.Google ScholarDigital Library
- Jonathan L Freedman and David O Sears. 1965. Selective exposure. In Advances in experimental social psychology. Vol. 2. Elsevier, 57–97.Google Scholar
- Mingkun Gao, Ziang Xiao, Karrie Karahalios, and Wai-Tat Fu. 2018. To Label or Not to Label: The Effect of Stance and Credibility Labels on Readers’ Selection and Perception of News Articles. Proceedings of the ACM on Human-Computer Interaction 2, CSCW(2018), 55:1–55:16. https://doi.org/10.1145/3274324Google ScholarDigital Library
- Edouard Grave, Piotr Bojanowski, Prakhar Gupta, Armand Joulin, and Tomas Mikolov. 2018. Learning word vectors for 157 languages. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018).Google Scholar
- Oliver Guhr, Anne-Kathrin Schumann, Frank Bahrmann, and Hans Joachim Böhme. 2020. Training a Broad-Coverage German Sentiment Classification Model for Dialog Systems. In Proceedings of the 12th Language Resources and Evaluation Conference. European Language Resources Association, Marseille, France, 1627–1632.Google Scholar
- Mario Haim, Andreas Graefe, and Hans-Bernd Brosius. 2018. Burst of the filter bubble? Effects of personalization on the diversity of Google News. Digital journalism 6, 3 (2018), 330–343.Google Scholar
- Felix Hamborg, Karsten Donnay, and Bela Gipp. 2019. Automated identification of media bias in news articles: an interdisciplinary literature review. International Journal on Digital Libraries 20, 4 (2019), 391–415.Google ScholarCross Ref
- Andreas Hanselowski, Avinesh P. V. S., Benjamin Schiller, Felix Caspelherr, Debanjan Chaudhuri, Christian M. Meyer, and Iryna Gurevych. 2018. A Retrospective Analysis of the Fake News Challenge Stance-Detection Task. In Proceedings of the 27th International Conference on Computational Linguistics, COLING 2018, Santa Fe, New Mexico, USA, August 20-26, 2018. Association for Computational Linguistics, 1859–1874. https://aclanthology.org/C18-1158/Google Scholar
- Natali Helberger. 2019. On the democratic role of news recommenders. Digital Journalism 7, 8 (2019), 993–1012.Google ScholarCross Ref
- Andreea Iana, Mehwish Alam, and Heiko Paulheim. 2022. A Survey On Knowledge-Aware News Recommender Systems. Semantic Web Journal(2022).Google Scholar
- Andreea Iana, Alexander Grote, Kaharina Ludwig, Mehwish Alam, Philipp Müller, Christof Weinhardt, Harald Sack, and Heiko Paulheim. 2022. GeNeG: German News Knowledge Graph. https://doi.org/10.5281/zenodo.5913171Google Scholar
- Kathleen Hall Jamieson and Joseph N Cappella. 2008. Echo chamber: Rush Limbaugh and the conservative media establishment. Oxford University Press.Google Scholar
- Mozhgan Karimi, Dietmar Jannach, and Michael Jugovac. 2018. News recommender systems–Survey and roads ahead. Information Processing & Management 54, 6 (2018), 1203–1227.Google ScholarCross Ref
- Dilek Küçük and Fazli Can. 2020. Stance Detection: A Survey. ACM Computing Surveys (CSUR) 53, 1 (2020), 12:1–12:37. https://doi.org/10.1145/3369026Google ScholarDigital Library
- Sora Lim, Adam Jatowt, Michael Färber, and Masatoshi Yoshikawa. 2020. Annotating and analyzing biased sentences in news articles using crowdsourcing. In Proceedings of the 12th Language Resources and Evaluation Conference. 1478–1484.Google Scholar
- Bing Liu 2010. Sentiment analysis and subjectivity.Handbook of natural language processing 2, 2010 (2010), 627–666.Google Scholar
- Ping Liu, Karthik Shivaram, Aron Culotta, Matthew A Shapiro, and Mustafa Bilgic. 2021. The Interaction between Political Typology and Filter Bubbles in News Recommendation Algorithms. In Proceedings of the Web Conference 2021. 3791–3801.Google ScholarDigital Library
- Katharina Ludwig, Alexander Grote, Andreea Iana, Mehwish Alam, Heiko Paulheim, Harald Sack, Christof Weinhardt, and Philipp Müller. 2022. Recommended Polarization? The (limited) effects of content- and sentiment-based news recommendation on affective, ideological, and perceived polarization. 72nd Annual ICA Conference, One World, One Network? (2022).Google Scholar
- Laura Mascarell, Tatyana Ruzsics, Christian Schneebeli, Philippe Schlattner, Luca Campanella, Severin Klingler, and Cristina Kadar. 2021. Stance Detection in German News Articles. In Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER). Association for Computational Linguistics, Dominican Republic, 66–77. https://doi.org/10.18653/v1/2021.fever-1.8Google ScholarCross Ref
- Philip May. 2020. Cross English & German RoBERTa for Sentence Embeddings. https://huggingface.co/T-Systems-onsite/cross-en-de-roberta-sentence-transformerGoogle Scholar
- Denis McQuail. 1992. Media performance: Mass communication and the public interest. Vol. 144. Sage London.Google Scholar
- Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781(2013).Google Scholar
- Saif Mohammad, Svetlana Kiritchenko, Parinaz Sobhani, Xiao-Dan Zhu, and Colin Cherry. 2016. A Dataset for Detecting Stance in Tweets. In Proceedings of the Tenth International Conference on Language Resources and Evaluation LREC 2016, Portorož, Slovenia, May 23-28, 2016. European Language Resources Association (ELRA).Google Scholar
- Eli Pariser. 2011. The filter bubble: What the Internet is hiding from you. Penguin UK.Google ScholarDigital Library
- Evaggelia Pitoura, Kostas Stefanidis, and Georgia Koutrika. 2021. Fairness in Rankings and Recommendations: An Overview. The VLDB Journal (2021), 1–28.Google ScholarDigital Library
- Kumar Ravi and Vadlamani Ravi. 2015. A survey on opinion mining and sentiment analysis: tasks, approaches and applications. Knowledge-based systems 89 (2015), 14–46.Google Scholar
- Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 3982–3992.Google ScholarCross Ref
- Myrthe Reuver, Antske Fokkens, Suzan Verberne, H Toivonen, and M Boggia. 2021. No NLP task should be an island: multi-disciplinarity for diversity in news recommender systems. Proceedings of the EACL Hackashop on news media content analysis and automated report generation(2021), 45–55.Google Scholar
- Arjun Roy, Pavlos Fafalios, Asif Ekbal, Xiaofei Zhu, and Stefan Dietze. 2022. Exploiting stance hierarchies for cost-sensitive stance detection of Web documents. Journal of Intelligent Information Systems 58, 1 (2022), 1–19.Google ScholarDigital Library
- Hinrich Schütze, Christopher D Manning, and Prabhakar Raghavan. 2008. Introduction to information retrieval. Vol. 39. Cambridge University Press Cambridge.Google Scholar
- Timo Spinde, Felix Hamborg, and Bela Gipp. 2020. An integrated approach to detect media bias in german news articles. In Proceedings of the ACM/IEEE joint conference on digital libraries in 2020. 505–506.Google ScholarDigital Library
- Natalie Jomini Stroud. 2017. Selective exposure theories. In The Oxford handbook of political communication.Google Scholar
- Cass R Sunstein. 2001. Echo chambers: Bush v. Gore, impeachment, and beyond. Princeton University Press Princeton, NJ.Google Scholar
- Jannis Vamvas and Rico Sennrich. 2020. X-Stance: A Multilingual Multi-Target Dataset for Stance Detection. CoRR abs/2003.08385(2020). arXiv:2003.08385https://arxiv.org/abs/2003.08385Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017).Google Scholar
- Paul S Voakes, Jack Kapfer, David Kurpius, and David Shano-yeon Chern. 1996. Diversity in the news: A conceptual and methodological framework. Journalism & Mass Communication Quarterly 73, 3 (1996), 582–593.Google ScholarCross Ref
- Denny Vrandečić and Markus Krötzsch. 2014. Wikidata: a free collaborative knowledgebase. Commun. ACM 57, 10 (2014), 78–85.Google ScholarDigital Library
- Hongwei Wang, Fuzheng Zhang, Jialin Wang, Miao Zhao, Wenjie Li, Xing Xie, and Minyi Guo. 2018. Ripplenet: Propagating user preferences on the knowledge graph for recommender systems. In Proceedings of the 27th ACM international conference on information and knowledge management. 417–426.Google ScholarDigital Library
- Ruifeng Xu, Yu Zhou, Dongyin Wu, Lin Gui, Jiachen Du, and Yun Xue. 2016. Overview of NLPCC Shared Task 4: Stance Detection in Chinese Microblogs. In Natural Language Understanding and Intelligent Applications - 5th CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2016, and 24th International Conference on Computer Processing of Oriental Languages, ICCPOL 2016, Kunming, China, December 2-6, 2016, Proceedings(Lecture Notes in Computer Science, Vol. 10102). Springer, 907–916. https://doi.org/10.1007/978-3-319-50496-4_85Google ScholarCross Ref
Index Terms
- Towards Analyzing the Bias of News Recommender Systems Using Sentiment and Stance Detection
Recommendations
Assessing Sentiment of the Expressed Stance on Social Media
Social InformaticsAbstractStance detection is the task of inferring viewpoint towards a given topic or entity either being supportive or opposing. One may express a viewpoint towards a topic by using positive or negative language. This paper examines how the stance is ...
Opinion-enhanced collaborative filtering for recommender systems through sentiment analysis
Advances in Social MediaThe motivation of collaborative filtering CF comes from the idea that people often get the best recommendations from someone with similar tastes. With the growing popularity of opinion-rich resources such as online reviews, new opportunities arise as we ...
Short Review of Sentiment-Based Recommender Systems
DTUC '18: Proceedings of the 1st International Conference on Digital Tools & Uses CongressSentiment analysis is a trendy domain of Machine Learning which has developed considerably in the last several years. It helps to determine the sentiment of a user in an utterance, a document or a review. Some systems can extract the target of the ...
Comments