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

Abstract

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.

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

“…According to the moral prediction results in recent studies, foundations related to Care and Fairness were challenging to predict [18,66]. Our results again showed that moral values related to Care and Fairness are more complex to predict than values related to Authority, Purity, and Loyalty.…”

“…People who value more Individualising values preferred artists whose songs' lyrics talk about joy, anticipation and trust. Those concerned more about ingroup and Binding values liked artists whose songs contained more romantic topics and disliked lyrics that implied negative emotions such as sadness, fear, or disgust [18]. However, as in the previous studies [55,66], the Individualising foundations remained challenging to predict.…”

“…In recent work, Preniqi et al [18] investigated moral values inferences based on a set of textual features related to lyrics' overarching narrative, moral valence, sentiment and songs' word emotion associations. The study demonstrated that lyrics components extracted from the naturally emerging music preferences in social media, to some degree, allow for constructing reliable premises of moral values.…”

“…As a metric for performance evaluation, we used Pearson's correlation coefficients between the predicted and actual moral values scores. This metric was commonly used in previous research on predicting psychological traits based on music preferences [6,7,18].…”

“…Similarly, song lyrics have also received little attention in personality science (e.g., [16,17]. In our previous work [18], we investigated the link between moral values and music preferences in terms of lyrics. Here we want to see how audio features perform in inferring moral values and whether we can improve our previous findings by combining lyrics and audio.…”