Exploiting Negative Preference in Content-based Music Recommendation with Contrastive Learning

TL;DR

This paper investigates the role of negative user preferences in music recommendation systems using contrastive learning, demonstrating that models exploiting negative preferences alone improve accuracy and stability across different features.

Contribution

It introduces a contrastive learning framework that effectively exploits negative preferences in music recommendation, with three training strategies and comprehensive validation.

Findings

CLEP-N outperforms other strategies in accuracy

Negative preference exploitation reduces false positives

Method is stable across different feature extractors

Abstract

Advanced music recommendation systems are being introduced along with the development of machine learning. However, it is essential to design a music recommendation system that can increase user satisfaction by understanding users' music tastes, not by the complexity of models. Although several studies related to music recommendation systems exploiting negative preferences have shown performance improvements, there was a lack of explanation on how they led to better recommendations. In this work, we analyze the role of negative preference in users' music tastes by comparing music recommendation models with contrastive learning exploiting preference (CLEP) but with three different training strategies - exploiting preferences of both positive and negative (CLEP-PN), positive only (CLEP-P), and negative only (CLEP-N). We evaluate the effectiveness of the negative preference by validating each system with a small amount of personalized data obtained via survey and further illuminate the possibility of exploiting negative preference in music recommendations. Our experimental results show that CLEP-N outperforms the other two in accuracy and false positive rate. Furthermore, the proposed training strategies produced a consistent tendency regardless of different types of front-end musical feature extractors, proving the stability of the proposed method.