Diversity, Fairness, and Data-Driven Personalization in (News) Recommender System external link

Bernstein, A., Vreese, C.H. de, Helberger, N., Schulz, W. & Zweig, K.A.
Dagstuhl Reports, vol. 9, num: 11, pp: 117-124, 2020

Abstract

As people increasingly rely on online media and recommender systems to consume information, engage in debates and form their political opinions, the design goals of online media and news recommenders have wide implications for the political and social processes that take place online and offline. Current recommender systems have been observed to promote personalization and more effective forms of informing, but also to narrow the user’s exposure to diverse content. Concerns about echo-chambers and filter bubbles highlight the importance of design metrics that can successfully strike a balance between accurate recommendations that respond to individual information needs and preferences, while at the same time addressing concerns about missing out important information, context and the broader cultural and political diversity in the news, as well as fairness. A broader, more sophisticated vision of the future of personalized recommenders needs to be formed–a vision that can only be developed as the result of a collaborative effort by different areas of academic research (media studies, computer science, law and legal philosophy, communication science, political philosophy, and democratic theory). The proposed workshop will set first steps to develop such a much needed vision on the role of recommender systems on the democratic role of the media and define the guidelines as well as a manifesto for future research and long-term goals for the emerging topic of fairness, diversity, and personalization in recommender systems.

diversity, fairness, frontpage, Mediarecht, personalisatie, recommender systems

Bibtex

Article{Bernstein2020, title = {Diversity, Fairness, and Data-Driven Personalization in (News) Recommender System}, author = {Bernstein, A. and Vreese, C.H. de and Helberger, N. and Schulz, W. and Zweig, K.A.}, url = {https://www.ivir.nl/publicaties/download/dagrep_v009_i011_p117_19482.pdf}, doi = {https://doi.org/10.4230/DagRep.9.11.117}, year = {0402}, date = {2020-04-02}, journal = {Dagstuhl Reports}, volume = {9}, number = {11}, pages = {117-124}, abstract = {As people increasingly rely on online media and recommender systems to consume information, engage in debates and form their political opinions, the design goals of online media and news recommenders have wide implications for the political and social processes that take place online and offline. Current recommender systems have been observed to promote personalization and more effective forms of informing, but also to narrow the user’s exposure to diverse content. Concerns about echo-chambers and filter bubbles highlight the importance of design metrics that can successfully strike a balance between accurate recommendations that respond to individual information needs and preferences, while at the same time addressing concerns about missing out important information, context and the broader cultural and political diversity in the news, as well as fairness. A broader, more sophisticated vision of the future of personalized recommenders needs to be formed–a vision that can only be developed as the result of a collaborative effort by different areas of academic research (media studies, computer science, law and legal philosophy, communication science, political philosophy, and democratic theory). The proposed workshop will set first steps to develop such a much needed vision on the role of recommender systems on the democratic role of the media and define the guidelines as well as a manifesto for future research and long-term goals for the emerging topic of fairness, diversity, and personalization in recommender systems.}, keywords = {diversity, fairness, frontpage, Mediarecht, personalisatie, recommender systems}, }

Know you algorithm: what media organizations need to explain to their users about news personalization external link

International Data Privacy Law, vol. 2019, 2019

Abstract

Key Points: - If the right to an explanation is expected to effectively safeguard users’ rights, it must be interpreted in a manner that takes the contextual risks algorithms pose to those rights into account. - This article provides a framework of transparency instruments in the context of the news personalization algorithms employed by both traditional media organizations and social media companies. - Explaining the impact on a user’s news diet and the role of editorial values in the algorithm is especially important in this context. - Conversely, explanations of individual decisions and counterfactual explanations face specific practical and normative barriers that limit their utility.

algoritmes, frontpage, Journalistiek, medialaw, personalisatie

Bibtex

Article{Drunen2019, title = {Know you algorithm: what media organizations need to explain to their users about news personalization}, author = {Drunen, M. van and Helberger, N. and Bastian, M.}, url = {https://academic.oup.com/idpl/advance-article/doi/10.1093/idpl/ipz011/5544759}, doi = {https://doi.org/10.1093/idpl/ipz011}, year = {1001}, date = {2019-10-01}, journal = {International Data Privacy Law}, volume = {2019}, pages = {}, abstract = {Key Points: - If the right to an explanation is expected to effectively safeguard users’ rights, it must be interpreted in a manner that takes the contextual risks algorithms pose to those rights into account. - This article provides a framework of transparency instruments in the context of the news personalization algorithms employed by both traditional media organizations and social media companies. - Explaining the impact on a user’s news diet and the role of editorial values in the algorithm is especially important in this context. - Conversely, explanations of individual decisions and counterfactual explanations face specific practical and normative barriers that limit their utility.}, keywords = {algoritmes, frontpage, Journalistiek, medialaw, personalisatie}, }

Algoritmische verzuiling en filter bubbles: een bedreiging voor de democratie? external link

Zuiderveen Borgesius, F., Trilling, D., Möller, J., Eskens, S., Bodó, B., Vreese, C.H. de & Helberger, N.
Computerrecht, vol. 2016, num: 5, pp: 255-262, 2016

algoritmen, democratie, filter bubbles, nieuws, personalisatie

Bibtex

Article{Borgesius2016b, title = {Algoritmische verzuiling en filter bubbles: een bedreiging voor de democratie?}, author = {Zuiderveen Borgesius, F. and Trilling, D. and Möller, J. and Eskens, S. and Bodó, B. and Vreese, C.H. de and Helberger, N.}, url = {https://www.ivir.nl/publicaties/download/Computerrecht_2016_5.pdf}, year = {1003}, date = {2016-10-03}, journal = {Computerrecht}, volume = {2016}, number = {5}, pages = {255-262}, keywords = {algoritmen, democratie, filter bubbles, nieuws, personalisatie}, }