Reading Between the Lines: A Study of Thematic Bias in Book Recommender Systems

TL;DR

This study investigates thematic bias in book recommender systems, revealing how content imbalances and user engagement patterns influence bias, and highlights the need for more inclusive recommendation strategies.

Contribution

It introduces a multi-stage framework for evaluating thematic bias and demonstrates its impact on different user groups, advancing responsible AI practices.

Findings

Thematic bias stems from content imbalances.

User engagement amplifies existing biases.

Niche users receive less personalized recommendations.

Abstract

Recommender systems help users discover new content, but can also reinforce existing biases, leading to unfair exposure and reduced diversity. This paper introduces and investigates thematic bias in book recommendations, defined as a disproportionate favouring or neglect of certain book themes. We adopt a multi-stage bias evaluation framework using the Book-Crossing dataset to evaluate thematic bias in recommendations and its impact on different user groups. Our findings show that thematic bias originates from content imbalances and is amplified by user engagement patterns. By segmenting users based on their thematic preferences, we find that users with niche and long-tail interests receive less personalised recommendations, whereas users with diverse interests receive more consistent recommendations. These findings suggest that recommender systems should be carefully designed to accommodate a broader range of user interests. By contributing to the broader goal of responsible AI, this work also lays the groundwork for extending thematic bias analysis to other domains.