Harm Mitigation in Recommender Systems under User Preference Dynamics

2024/06/14 by Jerry Chee, Shankar Kalyanaraman, Chee, Jerry +9 · 2 citations
Decision Sciences · #Advanced Bandit Algorithms Research #Computers and Society (cs.CY) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2406.09882

openalex publication_date 2024/06/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We consider a recommender system that takes into account the interplay between recommendations, the evolution of user interests, and harmful content. We model the impact of recommendations on user behavior, particularly the tendency to consume harmful content. We seek recommendation policies that establish a tradeoff between maximizing click-through rate (CTR) and mitigating harm. We establish conditions under which the user profile dynamics have a stationary point, and propose algorithms for finding an optimal recommendation policy at stationarity. We experiment on a semi-synthetic movie recommendation setting initialized with real data and observe that our policies outperform baselines at simultaneously maximizing CTR and mitigating harm.

Cited by

• Datasets for Navigating Sensitive Topics in Recommendation Systems
• You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control

Related

• Recommendation and Temptation
• Reactive Users vs. Social Recommender Systems: Managing Opinion Drifts with Adaptive Policies
• The Feedback Loop Between Recommendation Systems and Reactive Users
• Deconstructing the Filter Bubble: User Decision-Making and Recommender Systems
• Modeling Churn in Recommender Systems with Aggregated Preferences