Socially-Aware Recommender Systems Mitigate Opinion Clusterization

ICLR 2026 Conference Submission20550 Authors

Keywords: opinion dynamics, recommender systems, model predictive control, dynamical systems, networked systems

TL;DR: recommender system design aware about the dynamical feedback interaction between users and creators to mitigate opinion polarization

Abstract: Recommender systems shape online interactions by matching users with creators’ content to maximize engagement. Creators, in turn, adapt their content to align with users’ preferences and enhance their popularity. At the same time, users’ preferences evolve under the influence of both suggested content from the recommender system and content shared within their social circles. This feedback loop generates a complex interplay between users, creators, and recommender algorithms, which is the key cause of filter bubbles and opinion polarization. We develop a social network-aware recommender system that explicitly accounts for this users-creators feedback interaction and strategically exploits the topology of the user's own social network to promote diversification. Our approach highlights how accounting and exploiting user's social network in the recommender system design is crucial to mediate filter bubbles effects while balancing content diversity with personalization. Provably, opinion clustering is positively correlated with the influence of recommended content on user opinions. Ultimately, the proposed approach shows the power of socially-aware recommender systems in combating opinion polarization and clusterization phenomena.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 20550