When lyrics outperform audio for music mood classification: A feature analysis

This paper builds upon and extends previous work on multi-modal mood classification (i.e., combining audio and lyrics) by analyzing in-depth those feature types that have shown to provide statistically significant improvements in the classification of individual mood categories. The dataset used in this study comprises 5,296 songs (with lyrics and audio for each) divided into 18 mood categories derived from user-generated tags taken from last.fm. These 18 categories show remarkable consistency with the popular Russell's mood model. In seven categories, lyric features significantly outperformed audio spectral features. In one category only, audio outperformed all lyric features types. A fine grained analysis of the significant lyric feature types indicates a strong and obvious semantic association between extracted terms and the categories. No such obvious semantic linkages were evident in the case where audio spectral features proved superior.