Taste or Addiction?: Using Play Logs to Infer Song Selection Motivation
This work addresses the challenge of understanding user motivations in music streaming for applications like recommendation systems, but it is incremental as it builds on existing topic-based models by adding an addiction component.
The paper tackles the problem of distinguishing between taste-based and addiction-driven music listening behaviors using play logs, proposing a probabilistic model that incorporates artist addiction and demonstrating its effectiveness on real-world datasets with qualitative insights into time-of-day patterns and artist popularity.
Online music services are increasing in popularity. They enable us to analyze people's music listening behavior based on play logs. Although it is known that people listen to music based on topic (e.g., rock or jazz), we assume that when a user is addicted to an artist, s/he chooses the artist's songs regardless of topic. Based on this assumption, in this paper, we propose a probabilistic model to analyze people's music listening behavior. Our main contributions are three-fold. First, to the best of our knowledge, this is the first study modeling music listening behavior by taking into account the influence of addiction to artists. Second, by using real-world datasets of play logs, we showed the effectiveness of our proposed model. Third, we carried out qualitative experiments and showed that taking addiction into account enables us to analyze music listening behavior from a new viewpoint in terms of how people listen to music according to the time of day, how an artist's songs are listened to by people, etc. We also discuss the possibility of applying the analysis results to applications such as artist similarity computation and song recommendation.