Feedback Loop and Bias Amplification in Recommender Systems

TL;DR

This paper investigates how feedback loops in recommender systems amplify popularity bias, leading to reduced diversity and homogenization, especially affecting minority users, through a simulation-based analysis.

Contribution

It introduces a simulation method to study feedback loop effects on bias amplification and analyzes its impact on diversity and user experience in recommender systems.

Findings

Feedback loops increase popularity bias amplification.

Bias amplification reduces diversity and homogenizes user experience.

Minority users are more affected by feedback loop effects.

Abstract

Recommendation algorithms are known to suffer from popularity bias; a few popular items are recommended frequently while the majority of other items are ignored. These recommendations are then consumed by the users, their reaction will be logged and added to the system: what is generally known as a feedback loop. In this paper, we propose a method for simulating the users interaction with the recommenders in an offline setting and study the impact of feedback loop on the popularity bias amplification of several recommendation algorithms. We then show how this bias amplification leads to several other problems such as declining the aggregate diversity, shifting the representation of users' taste over time and also homogenization of the users experience. In particular, we show that the impact of feedback loop is generally stronger for the users who belong to the minority group.