User-Creator Feature Polarization in Recommender Systems with Dual Influence
This addresses a critical issue for recommender system designers and users by revealing unexpected failures in standard mitigation strategies, though it is incremental as it builds on existing models of influence.
The paper tackled the problem of polarization and diversity loss in recommender systems due to dual influence on users and creators, finding that common diversity-promoting approaches fail, while relevancy-optimizing methods like top-k truncation can prevent polarization and improve diversity.
Recommender systems serve the dual purpose of presenting relevant content to users and helping content creators reach their target audience. The dual nature of these systems naturally influences both users and creators: users' preferences are affected by the items they are recommended, while creators may be incentivized to alter their content to attract more users. We define a model, called user-creator feature dynamics, to capture the dual influence of recommender systems. We prove that a recommender system with dual influence is guaranteed to polarize, causing diversity loss in the system. We then investigate, both theoretically and empirically, approaches for mitigating polarization and promoting diversity in recommender systems. Unexpectedly, we find that common diversity-promoting approaches do not work in the presence of dual influence, while relevancy-optimizing methods like top-$k$ truncation can prevent polarization and improve diversity of the system.