Source Echo Chamber: Exploring the Escalation of Source Bias in User, Data, and Recommender System Feedback Loop

2024-05-28

arXiv.org

AI Summary

This paper identifies how source bias induced by AI-generated content (AIGC) in recommender systems is perpetuated and amplified through a user–data–model feedback loop, forming a “digital echo chamber”: short-term effects include over-preference for AIGC and unfair traffic allocation, while long-term consequences entail content homogenization and degraded recommendation performance. Method: We systematically characterize the evolutionary dynamics of source bias across three feedback-loop phases—human-generated content (HGC)-dominant → coexistence → AIGC-dominant—and propose a black-box, source-agnostic debiasing framework that requires no access to content provenance labels. Our approach integrates multi-domain empirical analysis, feedback-loop modeling, and neural recommendation model bias diagnosis. Contribution/Results: Experiments demonstrate that our method significantly mitigates AIGC overexposure, restores recommendation fairness between HGC and AIGC, and effectively alleviates the echo chamber effect.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Machine Learning: Ethics, Bias, and Fairness

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Recently, researchers have uncovered that neural retrieval models prefer AI-generated content (AIGC), called source bias. Compared to active search behavior, recommendation represents another important means of information acquisition, where users are more prone to source bias. Furthermore, delving into the recommendation scenario, as AIGC becomes integrated within the feedback loop involving users, data, and the recommender system, it progressively contaminates the candidate items, the user interaction history, and ultimately, the data used to train the recommendation models. How and to what extent the source bias affects the neural recommendation models within feedback loop remains unknown. In this study, we extend the investigation of source bias into the realm of recommender systems, specifically examining its impact across different phases of the feedback loop. We conceptualize the progression of AIGC integration into the recommendation content ecosystem in three distinct phases-HGC dominate, HGC-AIGC coexist, and AIGC dominance-each representing past, present, and future states, respectively. Through extensive experiments across three datasets from diverse domains, we demonstrate the prevalence of source bias and reveal a potential digital echo chamber with source bias amplification throughout the feedback loop. This trend risks creating a recommender ecosystem with limited information source, such as AIGC, being disproportionately recommended. To counteract this bias and prevent its escalation in the feedback loop, we introduce a black-box debiasing method that maintains model impartiality towards both HGC and AIGC. Our experimental results validate the effectiveness of the proposed debiasing method, confirming its potential to disrupt the feedback loop.

Problem

• Investigates source bias in recommender systems with AI-generated content.
• Examines short-term and long-term impacts of AIGC on recommendation dynamics.
• Proposes debiasing method to balance AIGC and human-generated content.

Innovation

• Incorporates AIGC to explore short-term impact
• Introduces feedback loop with realistic simulators
• Proposes L1-loss optimization for debiasing