Evolution of Popularity Bias: Empirical Study and Debiasing

TL;DR

This paper investigates how popularity bias evolves over time in dynamic recommender systems, revealing its impact and proposing a novel debiasing method that improves long-term recommendation fairness.

Contribution

It introduces the first empirical analysis of popularity bias in dynamic settings and proposes a new debiasing strategy and false positive correction method.

Findings

Popularity bias increases over time in dynamic scenarios.

The proposed debiasing method effectively reduces bias in long-term recommendations.

False positive signals can be leveraged to improve debiasing accuracy.

Abstract

Popularity bias is a long-standing challenge in recommender systems. Such a bias exerts detrimental impact on both users and item providers, and many efforts have been dedicated to studying and solving such a bias. However, most existing works situate this problem in a static setting, where the bias is analyzed only for a single round of recommendation with logged data. These works fail to take account of the dynamic nature of real-world recommendation process, leaving several important research questions unanswered: how does the popularity bias evolve in a dynamic scenario? what are the impacts of unique factors in a dynamic recommendation process on the bias? and how to debias in this long-term dynamic process? In this work, we aim to tackle these research gaps. Concretely, we conduct an empirical study by simulation experiments to analyze popularity bias in the dynamic scenario and propose a dynamic debiasing strategy and a novel False Positive Correction method utilizing false positive signals to debias, which show effective performance in extensive experiments.