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

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.

appeared at FAccT '20

References in corpus (6)

• Actionable Recourse in Linear Classification
• Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches
• On the Difficulty of Evaluating Baselines: A Study on Recommender Systems
• Combating the Cold Start User Problem in Model Based Collaborative Filtering
• When Collaborative Filtering Meets Reinforcement Learning
• Sequential Learning over Implicit Feedback for Robust Large-Scale Recommender Systems

Cited by in corpus (13)

• Rewiring What-to-Watch-Next Recommendations to Reduce Radicalization Pathways
• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
• Exploring Artist Gender Bias in Music Recommendation
• Measuring Recommender System Effects with Simulated Users
• From Explanation to Recommendation: Ethical Standards for Algorithmic Recourse
• On component interactions in two-stage recommender systems
• RecRec: Algorithmic Recourse for Recommender Systems
• When the Umpire is also a Player: Bias in Private Label Product Recommendations on E-commerce Marketplaces
• T-RECS: A Simulation Tool to Study the Societal Impact of Recommender Systems
• The Stereotyping Problem in Collaboratively Filtered Recommender Systems
• Linear Classifiers that Encourage Constructive Adaptation
• Causal Inference Struggles with Agency on Online Platforms
• Collaborative Filtering under Model Uncertainty