Music discovery and revisiting behaviors of individuals with different preference characteristics: An experience sampling approach

Abstract

A mobile device‐enabled experience sampling study was conducted in which 44 participants answered questions about their music experiences 5 times a day for 2 weeks. Data regarding 4 aspects of their music‐related psychological traits—“music involvement,” “musical identity,” “preference diversity,” and “preference openness”—were also collected through a background questionnaire. A classification of music access modes was proposed based on the circumstances that lead to a music listening experience. A mixed regression analysis revealed several significant interaction effects between psychological traits and the mode of music access on music enjoyment. Foremost among these was a positive interaction effect between preference openness and the playing of a known track triggered by musical cues, and that between preference diversity and exposure to new music played by others. Individuals with a strong musical identity tended to enjoy music played of their own volition without any apparent triggers. Furthermore, a multimodal logistic regression analysis also revealed the relationships between these psychological traits and the likelihood of different music access modes. Preference diversity significantly increased the likelihood of music listening triggered by need arousal. The results support the proposition that users' music‐related psychological traits should be considered in personalized recommendation strategies.

Preference diversity and openness to novelty: Scales construction from the perspective of movie recommendation

“…We also found that openness to novelty had a much higher correlation with involvement in movies than preference diversity did. Similarly, a strong correlation between openness to novelty and involvement was reported for music preference (Tang & Jhang, 2020).…”

“…The activity of "browsing friends' bookshelves"; a relatively imprecise yet diverse book discovery strategy, was most effective for individuals with high reading diversity. Preference diversity was also introduced in a music experience sampling study that explored the relationship between users' psychological traits and their music revisiting and discovery behaviors (Tang & Jhang, 2020). The findings indicated that individuals with high preference diversity in music derived more enjoyment from new music introduced by others than from listening to music already familiar to them.…”

Personalized Art Work Recommendation System and Methods Based on User Interest Characteristics and Emotional Preferences

“…However, user data also contains special interests, and traditional algorithms set them as isolated points. The constructed model will exclude these points, causing significant errors in the prediction results [3]. In recent years, the K-means algorithm has attracted the attention of many scholars due to its simple and efficient clustering research.…”