Personality and the Interplay between Emotion and Genre in Music Preferences

Abstract

Research over several decades has demonstrated modest and moderately consistent relationships between personality and music preference, but has primarily relied on self-reported data and lab-based listening experiments. Recently, music preference research has begun to take advantage of online listening data from platforms such as Spotify and Last.fm in order to more directly link listening behavior to individual differences. This study extends this new line of research by investigating the associations between naturally occurring music listening behaviors and personality traits, utilizing listening data acquired from Last.fm. We examined social-tagging data by extracting tags related to musical genre and emotion from frequently listened tracks of each participant and clustered them into broader categories to study their association with OCEAN traits. We further evaluated preferences in terms of co-occurring genre and emotion tags and analyzed listening patterns over time to better understand natural patterns of listening as they relate to personality. Our results corroborated previous research and revealed several novel associations that could be used to provide more accurate and highly customized music recommendations, tailored to the user’s personality. Then, we comment on existing music preference frameworks and their relevance to naturally occurring music listening behavior. Finally, we compare and analyze the emotions derived from semantic tags and acoustic features, shedding light on the interplay between subjective and objective measures of emotions in music listening and how they relate to personality.