Recommendations and User Agency: The Reachability of Collaboratively-Filtered Information
This work addresses the issue of user agency and information availability in recommender systems, which is an incremental improvement in understanding model complexity and user control.
The paper tackles the problem of unintended consequences like filter bubbles in recommender systems by proposing a computationally efficient audit for top-N linear models based on user recourse and reachability, and demonstrates it empirically on a movie ratings dataset.
Recommender systems often rely on models which are trained to maximize accuracy in predicting user preferences. When the systems are deployed, these models determine the availability of content and information to different users. The gap between these objectives gives rise to a potential for unintended consequences, contributing to phenomena such as filter bubbles and polarization. In this work, we consider directly the information availability problem through the lens of user recourse. Using ideas of reachability, we propose a computationally efficient audit for top-$N$ linear recommender models. Furthermore, we describe the relationship between model complexity and the effort necessary for users to exert control over their recommendations. We use this insight to provide a novel perspective on the user cold-start problem. Finally, we demonstrate these concepts with an empirical investigation of a state-of-the-art model trained on a widely used movie ratings dataset.