A groundbreaking study has revealed an important link between personal musical preferences and moral values. The study used machine learning to analyze the lyrics and audio features of favorite songs and found that music has a significant impact on moral sentiments. More than 1,400 participants shared their favorite music for analysis, and the results showed that musical elements such as pitch and timbre are associated with certain moral values.
Researchers have found a strong link between people's musical tastes and their moral values, suggesting that music is more than just entertainment and can shape moral beliefs. A new study published in the journal PLOSONE on November 29 found a significant link between individuals’ musical preferences and their moral values, revealing the profound impact music can have on our moral compass.
The study, conducted by a team of scientists from Queen Mary University of London and the ISI Foundation in Turin, Italy, used machine learning techniques to analyze the lyrics and audio characteristics of individuals' favorite songs, revealing the complex interplay between music and morality.
Dr Charalampos Saitis, one of the study's senior authors and a lecturer in digital music processing in the School of Electrical Engineering and Computer Science at Queen Mary University of London, said: "Our study provides compelling evidence that musical preferences can serve as a window into an individual's moral values."
The study involved an existing dataset of more than 1,400 participants who filled out psychometric questionnaires, assessed their moral values, and provided information about their favorite artists through Facebook page likes. The researchers then extracted vocal and lyrical features from the top five songs by each participant's favorite artists.
The research team used ML algorithms to analyze the extracted features to predict participants' moral values. They employed various text processing techniques, including lexicon-based methods and BERT-based embeddings, to analyze narratives, moral values, emotions, and emotions in lyrics. Additionally, low- and high-level audio features provided via Spotify’s application programming interface (API) were used to understand the information encoded in participants’ music selections to enhance moral inferences.
The results showed that a combination of lyrics and audio features was better than basic demographic information in predicting personal ethics. Specifically, musical elements such as pitch and timbre were key factors in predicting values such as "caring" and "fairness," while emotions and emotions expressed in lyrics were more effective in predicting traits such as "loyalty," "authority" and "purity."
"Our findings demonstrate that music is more than just a source of entertainment or aesthetic pleasure, it is also a powerful medium for reflecting and shaping our moral emotions. By understanding this connection, we can open up new avenues for music-based interventions that promote positive moral development. The implications of this study extend beyond academic curiosities and have the potential to influence how we engage with and utilize music in all aspects of our lives." of the study Senior co-author Dr. Kyriaki Kalimeri, ISI Foundation Fellow, commented: "Our breakthrough could pave the way for applications such as personalized music experiences, innovative music therapy, and communication activities. Our study uncovered important connections between music and morality, paving the way for deeper understanding of the psychological aspects of musical experiences. We are excited to continue exploring this rich and uncharted territory."
This study used data from the LikeYouth Facebook app, a research-focused survey tool with over 64,000 participants primarily in Italy. Participants provided voluntary informed consent and completed various psychometric surveys, including the Moral Foundations Questionnaire (MFQ), in addition to sharing demographic data and Facebook page likes.