Towards Estimating Personal Values in Song Lyrics

TL;DR

This paper explores methods for estimating personal values expressed in song lyrics to improve music information retrieval and personalization, comparing human annotations with automated embedding-based estimates.

Contribution

It introduces a perspectivist annotation approach guided by social science theory and compares it with automated embedding methods for estimating values in lyrics.

Findings

Initial results show promising annotation quality.

Automated estimates correlate with human annotations.

Discussion of sampling and annotation challenges.

Abstract

Most music widely consumed in Western Countries contains song lyrics, with U.S. samples reporting almost all of their song libraries contain lyrics. In parallel, social science theory suggests that personal values - the abstract goals that guide our decisions and behaviors - play an important role in communication: we share what is important to us to coordinate efforts, solve problems and meet challenges. Thus, the values communicated in song lyrics may be similar or different to those of the listener, and by extension affect the listener's reaction to the song. This suggests that working towards automated estimation of values in lyrics may assist in downstream MIR tasks, in particular, personalization. However, as highly subjective text, song lyrics present a challenge in terms of sampling songs to be annotated, annotation methods, and in choosing a method for aggregation. In this project, we take a perspectivist approach, guided by social science theory, to gathering annotations, estimating their quality, and aggregating them. We then compare aggregated ratings to estimates based on pre-trained sentence/word embedding models by employing a validated value dictionary. We discuss conceptually 'fuzzy' solutions to sampling and annotation challenges, promising initial results in annotation quality and in automated estimations, and future directions.