Content filtering methods for music recommendation: A review

TL;DR

This review discusses content filtering techniques in music recommendation systems, emphasizing methods like lyrical analysis with LLMs and audio processing to overcome collaborative filtering limitations due to data sparsity.

Contribution

It provides a comprehensive overview of current content filtering methods, compares different song classification techniques, and suggests solutions for integrating diverse analysis approaches.

Findings

Content filtering helps mitigate collaborative filtering biases.

Lyrical analysis with LLMs offers new classification avenues.

Audio signal processing remains a key technique.

Abstract

Recommendation systems have become essential in modern music streaming platforms, shaping how users discover and engage with songs. One common approach in recommendation systems is collaborative filtering, which suggests content based on the preferences of users with similar listening patterns to the target user. However, this method is less effective on media where interactions are sparse. Music is one such medium, since the average user of a music streaming service will never listen to the vast majority of tracks. Due to this sparsity, there are several challenges that have to be addressed with other methods. This review examines the current state of research in addressing these challenges, with an emphasis on the role of content filtering in mitigating biases inherent in collaborative filtering approaches. We explore various methods of song classification for content filtering, including lyrical analysis using Large Language Models (LLMs) and audio signal processing techniques. Additionally, we discuss the potential conflicts between these different analysis methods and propose avenues for resolving such discrepancies.