Automatic Detection of Moral Values in Music Lyrics

TL;DR

This paper presents transformer-based models fine-tuned on synthetic lyrics to accurately detect moral values in real music lyrics, outperforming baselines and offering insights into moral expression in music.

Contribution

It introduces a novel approach using fine-tuned transformer models on synthetic data for morality detection in lyrics, achieving higher accuracy than existing methods.

Findings

Models achieved an average F1 score of 0.8, outperforming baselines.

Proposed models had 12% higher precision in binary classification.

Effective annotation-free morality detection in lyrics demonstrated.

Abstract

Moral values play a fundamental role in how we evaluate information, make decisions, and form judgements around important social issues. The possibility to extract morality rapidly from lyrics enables a deeper understanding of our music-listening behaviours. Building on the Moral Foundations Theory (MFT), we tasked a set of transformer-based language models (BERT) fine-tuned on 2,721 synthetic lyrics generated by a large language model (GPT-4) to detect moral values in 200 real music lyrics annotated by two experts.We evaluate their predictive capabilities against a series of baselines including out-of-domain (BERT fine-tuned on MFT-annotated social media texts) and zero-shot (GPT-4) classification. The proposed models yielded the best accuracy across experiments, with an average F1 weighted score of 0.8. This performance is, on average, 5% higher than out-of-domain and zero-shot models. When examining precision in binary classification, the proposed models perform on average 12% higher than the baselines.Our approach contributes to annotation-free and effective lyrics morality learning, and provides useful insights into the knowledge distillation of LLMs regarding moral expression in music, and the potential impact of these technologies on the creative industries and musical culture.