Evolution of moral expression in song lyrics

 

Building on this line of work, we asked a complementary question: if the music people like reveals something about their morality, what does six decades of popular music reveal about ours?

In a new study published in Scientific Reports, we analysed the moral content of hundreds of thousands of songs spanning 1960–2023, drawing on the WASABI corpus and Billboard year-end charts. Using transformer-based language models fine-tuned to predict the ten moral dimensions of Moral Foundations Theory, we tracked how moral narratives shifted across time, musical genres, and artist genders.

The trend is consistent and one-directional: expressions of moral vices rise sharply — Degradation (+52%), Harm (+49%), Cheating (+48%), Subversion (+41%) — while moral virtues decline: Care (−24%), Purity (−12%), Loyalty (−11%). These shifts are accompanied by a rise in negative sentiment, anger, and disgust. We also show that moral dimensions can be inferred from lyrical cues such as thematic content, sentiment, and emotion, with predictive accuracy improving markedly when models are trained within specific genres.

An important caveat: this work describes what songs express, not what listeners believe. Whether popular music shapes moral norms or merely reflects them is not something our design can adjudicate. What it does suggest is that popular music functions as a usable cultural barometer of evolving moral discourse.

Preniqi, V., Kaltenbrunner, A., Kalimeri, K., & Saitis, C. (2026). Evolution of moral expression in song lyrics. Scientific Reports, 16, 19556.
Read the full article (open access) at Scientific Reports · DOI: 10.1038/s41598-026-53778-9

In the media:

Soundscapes of morality: Linking music preferences and moral values through lyrics and audio

 

Musical-preferences

In collaboration with Vjosa Preniqi and Charalampos Saitis from Queen Mary University

Music is a fundamental element in every culture, serving as a universal means of expressing our emotions, feelings, and beliefs. This work investigates the link between our moral values and musical choices through lyrics and audio analyses. We align the psychometric scores of 1,480 participants to acoustics and lyrics features obtained from the top 5 songs of their preferred music artists from Facebook Page Likes. We employ a variety of lyric text processing techniques, including lexicon-based approaches and BERT-based embeddings, to identify each song’s narrative, moral valence, attitude, and emotions. In addition, we extract both low- and high-level audio features to comprehend the encoded information in participants’ musical choices and improve the moral inferences. 

We propose a Machine Learning approach and assess the predictive power of lyrical and acoustic features separately and in a multimodal framework for predicting moral values. Results indicate that lyrics and audio features from the artists people like inform us about their morality. Though the most predictive features vary per moral value, the models that utilised a combination of lyrics and audio characteristics were the most successful in predicting moral values, outperforming the models that only used basic features such as user demographics, the popularity of the artists, and the number of likes per user. Audio features boosted the accuracy in the prediction of empathy and equality compared to textual features, while the opposite happened for hierarchy and tradition, where higher prediction scores were driven by lyrical features. This demonstrates the importance of both lyrics and audio features in capturing moral values. The insights gained from our study have a broad range of potential uses, including customising the music experience to meet individual needs, music rehabilitation, or even effective communication campaign crafting.

Read the full article at PLOS ONE