Unmasking Gender Bias in Recommendation Systems and Enhancing Category-Aware Fairness

2025-02-25

AI Summary

Gender bias in recommender systems is often masked at the item-category level (e.g., movie genres), rendering conventional group-level fairness metrics insufficient. Method: This paper proposes the first category-aware, fine-grained fairness evaluation and optimization framework. It (1) establishes a semantic-category-based gender bias quantification metric suite; (2) designs category-weighted bias measures and cross-group category distribution disparity analysis; and (3) incorporates category-aware fairness as a regularization term into training objectives of multiple recommendation models (e.g., MF, LightGCN). Contribution/Results: Experiments on three real-world datasets demonstrate that the proposed metrics uncover fine-grained biases invisible to standard group-level fairness measures. With fairness regularization, average category-level fairness improves by 37%, while recommendation accuracy degrades by less than 1.2%—significantly outperforming baselines.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Ethics, Bias, and Fairness
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems

Abstract

Recommendation systems are now an integral part of our daily lives. We rely on them for tasks such as discovering new movies, finding friends on social media, and connecting job seekers with relevant opportunities. Given their vital role, we must ensure these recommendations are free from societal stereotypes. Therefore, evaluating and addressing such biases in recommendation systems is crucial. Previous work evaluating the fairness of recommended items fails to capture certain nuances as they mainly focus on comparing performance metrics for different sensitive groups. In this paper, we introduce a set of comprehensive metrics for quantifying gender bias in recommendations. Specifically, we show the importance of evaluating fairness on a more granular level, which can be achieved using our metrics to capture gender bias using categories of recommended items like genres for movies. Furthermore, we show that employing a category-aware fairness metric as a regularization term along with the main recommendation loss during training can help effectively minimize bias in the models' output. We experiment on three real-world datasets, using five baseline models alongside two popular fairness-aware models, to show the effectiveness of our metrics in evaluating gender bias. Our metrics help provide an enhanced insight into bias in recommended items compared to previous metrics. Additionally, our results demonstrate how incorporating our regularization term significantly improves the fairness in recommendations for different categories without substantial degradation in overall recommendation performance.

Problem

• Identify and measure gender bias in recommendation systems.
• Develop category-aware metrics for granular fairness evaluation.
• Enhance model fairness without compromising recommendation performance.

Innovation

• Category-aware fairness metrics
• Regularization term for bias minimization
• Granular gender bias evaluation