Transformer-based approach towards music emotion recognition from lyrics
This study offers an incremental improvement for music recommendation and playlist generation systems by enhancing the accuracy of emotion recognition from lyrics.
This paper addresses the task of music emotion recognition from lyrics by employing a transformer-based model using XLNet as the base architecture. The proposed approach achieved superior performance compared to existing methods across multiple datasets.
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.