Recommendations and User Agency: The Reachability of Collaboratively-Filtered Information

TL;DR

This paper investigates how the design of recommender systems impacts user agency and content accessibility, introducing an efficient audit method and analyzing the relationship between model complexity and user control.

Contribution

It presents a novel reachability-based audit for linear recommender models and explores how model complexity affects user ability to influence recommendations.

Findings

Efficient audit method for top-N linear recommenders

Model complexity correlates with user control effort

Empirical analysis on a popular movie ratings dataset

Abstract

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.