Transformer-based approach towards music emotion recognition from lyrics

TL;DR

This paper introduces a transformer-based model using XLNet for music emotion recognition from lyrics, outperforming existing methods and enhancing playlist and music recommendation systems.

Contribution

It is the first to apply XLNet, a transformer model, to music emotion recognition from lyrics, demonstrating superior performance over prior approaches.

Findings

Outperforms existing methods on multiple datasets.

Improves lyrics extraction accuracy from web sources.

Enhances music recommendation and playlist generation.

Abstract

The task of identifying emotions from a given music track has been an active pursuit in the Music Information Retrieval (MIR) community for years. Music emotion recognition has typically relied on acoustic features, social tags, and other metadata to identify and classify music emotions. The role of lyrics in music emotion recognition remains under-appreciated in spite of several studies reporting superior performance of music emotion classifiers based on features extracted from lyrics. In this study, we use the transformer-based approach model using XLNet as the base architecture which, till date, has not been used to identify emotional connotations of music based on lyrics. Our proposed approach outperforms existing methods for multiple datasets. We used a robust methodology to enhance web-crawlers' accuracy for extracting lyrics. This study has important implications in improving applications involved in playlist generation of music based on emotions in addition to improving music recommendation systems.