Sep 2026· Proceedings of the 20th ACM Conference on Recommender Systems· pp. 1920-1925· 0 citations· 29 references
TL;DR
This work reimagines recommender systems not merely as engines of engagement, but as accountable infrastructures that uphold democratic values that affect both individuals and society at large.
Abstract
Recommender systems shape how people shop, learn, and read the news, and advances in algorithms have made personalization increasingly influential. Yet most systems are optimized for accuracy and engagement without asking the normative question of what recommender systems should be. When we fail to ask this question, we risk systems that amplify misinformation, reinforce biases, and create echo chambers that affect both individuals and society at large. News recommendation is a powerful case in point: while it plays a pivotal role in shaping public opinion, current systems lack mechanisms to include journalists’ voices, values, and perspectives. My work addresses this gap through (1) a co-design methodology for eliciting and encoding journalistic values, (2) a values-aware reranking instantiation built on SCRUF-D, and (3) longitudinal field evaluation via POPROX. This work reimagines recommender systems not merely as engines of engagement, but as accountable infrastructures that uphold democratic values.
Large Language Models (LLMs) are increasingly used to evaluate recommendation systems, but are known to exhibit systematic biases. We study whether LLM judges are influenced by descriptions of a recommendation algorithm’s optimization objective, even when evaluating identical recommendation outputs. We find that they a...
Himan Abdollahpouri, Kyle Kretschman, M. Lalmas· Proceedings of the 20th ACM...· 0 citations
Personalized news recommendation systems often reinforce users' pre-existing beliefs by limiting their exposure, contributing to political echo chambers. Existing mitigation approaches—such as rewriting biased text or diversifying recommendations—risk distorting article semantics or deepening polarization, while typica...
Seongeun Ryu, Hoyeol Yang, Kayoung Lee et al.· Proceedings of the 35th ACM...· 0 citations
Real-world embodiments of recommender systems are increasingly often posed as decision-making systems, imposing consequences on the world around them. The literature on causal and counterfactual inference allows us to reason about these consequences, and better understand their implications. Whilst this research area h...
Olivier Jeunen, Harrie Oosterhuis, Flavian Vasile et al.· Proceedings of the 20th ACM...· 0 citations
Recommender systems increasingly influence what users discover and consume online, yet the decision logic behind their outputs often remains opaque. Counterfactual explanation (CFX) methods provide an effective way to show which changes to a user's interaction history would alter a recommendation. In recommendation set...
Vojtech Cahlík, Amir Reza Mohammadi, R. Alves et al.· Proceedings of the 35th ACM...· 0 citations
Recommender systems (RSs) are widely used to support users in discovering relevant items, yet their growing complexity raises concerns about transparency and interpretability. This work investigates the use of Large Language Models (LLMs) to generate automated, human-centered explanations for RSs and evaluates whether...
Ítallo De Sousa Silva· Anais do XV Concurso de Tese...· 0 citations
Misinformation is widely reported to propagate faster on engagement-based platforms, yet prior work largely focused on empirical analysis, without identifying a specific algorithmic mechanism that results in this phenomenon. Thanks to the open-sourcing of X's recommendation algorithms, we conduct what is, to our knowle...
Pan Li, Shuang Gao· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.