{"type":"ScholarlyArticle","title":"Rewiring What-to-Watch-Next Recommendations to Reduce Radicalization Pathways (Extended Abstract)","authors":[{"name":"Francesco Fabbri","slug":"francesco-fabbri","given":"Francesco","family":"Fabbri","affiliation":"Spotify , Barcelona , Spain"},{"name":"Yanhao Wang","slug":"yanhao-wang","given":"Yanhao","family":"Wang","affiliation":"East China Normal University , Shanghai , China"},{"name":"Francesco Bonchi","slug":"francesco-bonchi","given":"Francesco","family":"Bonchi","affiliation":"CENTAI Institute , Turin , Italy; Eurecat , Barcelona , Spain"},{"name":"Carlos Castillo","slug":"carlos-castillo","given":"Carlos","family":"Castillo","affiliation":"ICREA , Barcelona , Spain; Universitat Pompeu Fabra , Barcelona , Spain"},{"name":"Michael Mathioudakis","slug":"michael-mathioudakis","given":"Michael","family":"Mathioudakis","affiliation":"University of Helsinki , Helsinki , Finland"}],"abstract":"Recommender systems typically suggest to users content similar to what they consumed in the past. A user, if happening to be exposed to strongly polarized content, might be steered towards more and more radicalized content by subsequent recommendations, eventually being trapped in what we call a \"radicalization pathway\". In this paper, we investigate how to mitigate radicalization pathways using a graph-based approach. We model the set of recommendations in a what-to-watch-next (W2W) recommender as a directed graph, where nodes correspond to content items, links to recommendations, and paths to possible user sessions. We measure the segregation score of a node representing radicalized content as the expected length of a random walk from that node to any node representing non-radicalized content. A high segregation score thus implies a larger chance of getting users trapped in radicalization pathways. We aim to reduce the prevalence of radicalization pathways by selecting a small number of edges to rewire, so as to minimize the maximum of segregation scores among all radicalized nodes while maintaining the relevance of recommendations. We propose an efficient yet effective greedy heuristic based on the absorbing random walk theory for the rewiring problem. Our experiments on real-world datasets confirm the effectiveness of our proposal.","doi":"10.24963/ijcai.2023/715","url":"https://ijcai.org/proceedings/2023/715","pdf":"https://ijcai.org/proceedings/2023/0715.pdf","markdown":"https://ijcai.org/proceedings/2023/715.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/715","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Sister Conferences Best Papers","track":"Sister Conferences Best Papers","number":715,"pages":{"first":6431,"last":6435},"keywords":["Sister Conferences Best Papers: Humans and AI","Sister Conferences Best Papers: Data Mining","Sister Conferences Best Papers: AI Ethics, Trust, Fairness"],"videos":[],"references":[{"position":1,"raw":"[Biega et al., 2018] Asia J. Biega, Krishna P. Gummadi, and Gerhard Weikum. Equity of attention: Amortizing indi- vidual fairness in rankings. In Proceedings of the 41st In- ternational ACM SIGIR Conference on Research & Devel- opment in Information Retrieval, pages 405-414, 2018.","title":"Equity of attention: Amortizing individual fairness in rankings","authors":"Biega","year":"2018","venue":"Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cinus et al., 2022] Federico Cinus, Marco Minici, Corrado Monti, and Francesco Bonchi. The effect of people recom- menders on echo chambers and polarization. Proceedings of the International AAAI Conference on Web and Social Media, 16(1):90-101, 2022.","title":"The effect of people recommenders on echo chambers and polarization","authors":"Federico Cinus, Marco Minici, Corrado Monti, Francesco Bonchi","year":"2022","venue":"Proceedings of the International AAAI Conference on Web and Social Media","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Fabbri et al., 2022] Francesco Fabbri, Yanhao Wang, Francesco Bonchi, Carlos Castillo, and Michael Math- ioudakis. Rewiring what-to-watch-next recommendations to reduce radicalization pathways. In Proceedings of the ACM Web Conference 2022, pages 2719-2728, 2022.","title":"Rewiring what-to-watch-next recommendations to reduce radicalization pathways","authors":"Francesco Fabbri, Yanhao Wang, Francesco Bonchi, Carlos Castillo, Michael Mathioudakis","year":"2022","venue":"Proceedings of the ACM Web Conference 2022","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Haddadan et al., 2021] Shahrzad Haddadan, Cristina Menghini, Matteo Riondato, and Eli Upfal. RePBubLik: Reducing polarized bubble radius with link insertions. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, pages 139-147, 2021.","title":"RePBubLik: Reducing polarized bubble radius with link insertions","authors":"Shahrzad Haddadan, Cristina Menghini, Matteo Riondato, Eli Upfal","year":"2021","venue":"Proceedings of the 14th ACM International Conference on Web Search and Data Mining","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Haddadan et al., 2022] Shahrzad Haddadan, Cristina Menghini, Matteo Riondato, and Eli Upfal. Reducing polarization and increasing diverse navigability in graphs by inserting edges and swapping edge weights. Data Min. Knowl. Discov., 36(6):2334-2378, 2022.","title":"Reducing polarization and increasing diverse navigability in graphs by inserting edges and swapping edge weights","authors":"Shahrzad Haddadan, Cristina Menghini, Matteo Riondato, Eli Upfal","year":"2022","venue":"Data Min. Knowl. Discov","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hu et al., 2008] Yifan Hu, Yehuda Koren, and Chris Volin- sky. Collaborative filtering for implicit feedback datasets. In Proceedings of the 8th IEEE International Conference on Data Mining, pages 263-272, 2008.","title":"Collaborative filtering for implicit feedback datasets","authors":"Yifan Hu, Yehuda Koren, Chris Volinsky","year":"2008","venue":"Proceedings of the 8th IEEE International Conference on Data Mining","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Järvelin and Kekäläinen, 2002] Kalervo Järvelin and Jaana Kekäläinen. Cumulated gain-based evaluation of IR tech- niques. ACM Trans. Inf. Syst., 20(4):422-446, 2002.","title":"Cumulated gain-based evaluation of IR techniques","authors":"Järvelin, Kekäläinen, Kalervo Järvelin, Jaana Kekäläinen","year":"2002","venue":"ACM Trans. Inf. Syst","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ledwich and Zaitsev, 2020] Mark Ledwich and Anna Zait- sev. Algorithmic extremism: Examining YouTube's rabbit hole of radicalization. First Monday, 25(3), 2020.","title":"Algorithmic extremism: Examining YouTube's rabbit hole of radicalization","authors":"Zaitsev Ledwich, Mark Ledwich, Anna Zaitsev","year":"2020","venue":"First Monday","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lewis, 2018] Rebecca Lewis. Alternative influence: Broad- casting the reactionary right on YouTube. Technical report, Data & Society Research Institute, September 2018.","title":"Alternative influence: Broadcasting the reactionary right on YouTube","authors":"Rebecca Lewis","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Mavroforakis et al., 2015] Charalampos Mavroforakis, Michael Mathioudakis, and Aristides Gionis. Absorbing random-walk centrality: Theory and algorithms. In Proceedings of the 2015 IEEE International Conference on Data Mining, pages 901-906, 2015.","title":"Absorbing random-walk centrality: Theory and algorithms","authors":"Charalampos Mavroforakis, Michael Mathioudakis, Aristides Gionis","year":"2015","venue":"Proceedings of the 2015 IEEE International Conference on Data Mining","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[McCauley and Moskalenko, 2008] Clark McCauley and Sophia Moskalenko. Mechanisms of political radical- ization: Pathways toward terrorism. Terror. Political Violence, 20(3):415-433, 2008.","title":"Mechanisms of political radicalization: Pathways toward terrorism","authors":"Moskalenko Mccauley, Clark Mccauley, Sophia Moskalenko","year":"2008","venue":"Terror. Political Violence","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ribeiro et al., 2020] Manoel Horta Ribeiro, Raphael Ottoni, Robert West, Virgílio A. F. Almeida, and Wagner Meira Jr. Auditing radicalization pathways on YouTube. In Pro- ceedings of the 2020 Conference on Fairness, Account- ability, and Transparency, pages 131-141, 2020.","title":"Auditing radicalization pathways on YouTube","authors":"Raphael Manoel Horta Ribeiro, Robert Ottoni, West, A F Virgílio, Wagner Almeida, Meira","year":"2020","venue":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Roose, 2019] Kevin Roose. The making of a YouTube rad- ical. The New York Times, 2019.","title":"The making of a YouTube radical","authors":"Kevin Roose","year":"2019","venue":"The New York Times","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Weiss and Winter, 2018] Bari Weiss and Damon Winter. Meet the renegades of the intellectual dark web. The New York Times, 2018.","title":"Meet the renegades of the intellectual dark web","authors":"Winter ; Weiss, Bari Weiss, Damon Winter","year":"2018","venue":"The New York Times","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Zhao et al., 2019] Zhe Zhao, Lichan Hong, Li Wei, Jilin Chen, Aniruddh Nath, Shawn Andrews, Aditee Kumthekar, Maheswaran Sathiamoorthy, Xinyang Yi, and Ed H. Chi. Recommending what video to watch next: A multitask ranking system. In Proceedings of the 13th ACM Conference on Recommender Systems, pages 43-51, 2019.","title":"Recommending what video to watch next: A multitask ranking system","authors":"Zhe Zhao, Lichan Hong, Li Wei, Jilin Chen, Aniruddh Nath, Shawn Andrews, Aditee Kumthekar, Maheswaran Sathiamoorthy, Xinyang Yi, Ed H Chi","year":"2019","venue":"Proceedings of the 13th ACM Conference on Recommender Systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}