“‘Just the Way You Are’: Linking Music Listening on Spotify and Personality”, 2020-07-10 ():
Advances in digital technology have put music libraries at people’s fingertips, giving them immediate access to more music than ever before.
Here we overcome limitations of prior research by leveraging ecologically valid streaming data: 17.6 million songs and over 662,000 hr of music listened to by 5,808 Spotify users spanning a 3-month period.
Building on interactionist theories, we investigated the link between personality traits and music listening behavior, described by an extensive set of 211 mood, genre, demographic, and behavioral metrics. Findings from machine learning showed that the Big Five personality traits are predicted by musical preferences and habitual listening behaviors with moderate to high accuracy.
Importantly, our work contrasts a recent self-report-based meta-analysis, which suggested that personality traits play only a small role in musical preferences; rather, we show with big data and advanced machine learning methods that personality is indeed important and warrants continued rigorous investigation.
…Prediction: Mean of the RMSE from 10× cross-validation showed moderate to high prediction for each of the Big Five personality traits: 0.811 for Extraversion, 0.777 for Emotional Stability, 0.621 for Agreeableness, 0.618 for conscientiousness, and 0.53 for Openness. Independent regressions were then performed for each trait. Table 1 summarizes our prediction results (rs range 0.262–0.374). These results are greater in magnitude than those found in previous research by et al 2018 that use stimuli-based methods and Facebook likes to assess musical preferences. That our results yielded higher correlations is not surprising since we included metrics that assessed not only musical preferences but also habitual listening behaviors…Of the 5 personality traits, Emotional Stability and Conscientiousness were the 2 most predictable from our data (rs = 0.374 and 0.363, respectively).