Summary: A new study reveals a significant link between individuals’ musical tastes and their moral values.
Employing machine learning to analyze lyrics and audio features from participants’ favorite songs, the study found that music preferences reflect specific moral dimensions.
Using data from over 1,400 individuals, this research discovered that musical elements like pitch, timbre, and lyrical sentiments are key indicators of moral traits like Care, Fairness, Loyalty, Authority, and Purity.
These insights open potential avenues for personalized music experiences and music-based interventions in moral development.
Key Facts:
- The study establishes a connection between individuals’ musical preferences and their moral values, utilizing machine learning analysis.
- Key musical features such as pitch, timbre, and lyrical content were found to correlate with specific moral dimensions.
- The findings offer potential applications in personalized music experiences and innovative approaches to music therapy and moral development.
Source: Queen Mary University London
A new study, published in PLOS ONE, has uncovered a remarkable connection between individuals’ musical preferences and their moral values, shedding new light on the profound influence that music can have on our moral compass.
The research, conducted by a team of scientists at Queen Mary University of London and ISI Foundation in Turin, Italy, employed machine learning techniques to analyse the lyrics and audio features of individuals’ favorite songs, revealing a complex interplay between music and morality.
“Our study provides compelling evidence that music preferences can serve as a window into an individual’s moral values,” stated Dr Charalampos Saitis, one of the senior authors of the study and Lecturer in Digital Music Processing at Queen Mary University of London’s School of Electronic Engineering and Computer Science.
The study involved an existing dataset of over 1,400 participants who completed psychometric questionnaires assessing their moral values and provided information about their favorite artists through Facebook Page Likes. The researchers then extracted acoustic and lyrical features from the top five songs of each participant’s preferred artists.
Using ML algorithms, the team analysed the extracted features to predict participants’ moral values. Various text processing techniques, including lexicon-based methods and BERT-based embeddings, were employed to analyze narrative, moral values, sentiment, and emotions in lyrics.
Additionally, low- and high-level audio features provided via Spotify’s API were used to understand encoded information in participants’ musical choices, enhancing moral inferences.
The results demonstrated that a combination of lyrical and audio features outperformed basic demographic information in predicting individuals’ moral compass.
Specifically, musical elements like pitch and timbre emerged as crucial predictors for values of Care and Fairness, while sentiments and emotions expressed in lyrics were more effective in predicting traits of Loyalty, Authority, and Purity.
“Our findings reveal that music is not merely a source of entertainment or aesthetic pleasure; it is also a powerful medium that reflects and shapes our moral sensibilities,” remarked Vjosa Preniqi, lead author of the study and a PhD student in Queen Mary’s Centre for Doctoral Training in Data-informed Audience-centric Media Engineering.
“By understanding this connection, we can open up new avenues for music-based interventions that promote positive moral development.”
The study’s implications extend beyond mere academic curiosity, holding the potential to impact how we engage with and utilise music in diverse aspects of life.
“Our breakthrough can pave the way for applications ranging from personalised music experiences to innovative music therapy and communication campaigns,” commented Dr Kyriaki Kalimeri, senior co-author of the study and researcher at ISI Foundation.
“Our research has uncovered an important link between music and morality, paving the way for a deeper understanding of the psychological dimensions of our musical experiences,” concluded Vjosa Preniqi. “We are excited to continue exploring this rich and uncharted territory.”
This study was conducted using data from the LikeYouth Facebook application, a research-focused survey tool that has engaged over 64,000 participants primarily in Italy. Participants provided voluntary and informed consent and completed various psychometric surveys, including the Moral Foundations Questionnaire (MFQ), in addition to sharing demographic details and Facebook Page Likes.
About this music and psychology research news
Author: Ilyana Zolotareva
Source: Queen Mary University London
Contact: Ilyana Zolotareva – Queen Mary University London
Image: The image is credited to Neuroscience News
Original Research: Open access.
“Soundscapes of morality: Linking music preferences and moral values through lyrics and audio” by Charalampos Saitis et al. PLOS ONE
Abstract
Soundscapes of morality: Linking music preferences and moral values through lyrics and audio
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.
