Modeling Musical Genre Trajectories through Pathlet Learning
This work addresses the challenge of analyzing music consumption evolution for streaming platforms, with potential applications in improving recommender systems and user behavior research.
The paper tackles the problem of understanding how user musical preferences evolve over time by modeling genre trajectories using a new dictionary learning framework called pathlets, which reveals recurring listening patterns and enables trajectory embeddings.
The increasing availability of user data on music streaming platforms opens up new possibilities for analyzing music consumption. However, understanding the evolution of user preferences remains a complex challenge, particularly as their musical tastes change over time. This paper uses the dictionary learning paradigm to model user trajectories across different musical genres. We define a new framework that captures recurring patterns in genre trajectories, called pathlets, enabling the creation of comprehensible trajectory embeddings. We show that pathlet learning reveals relevant listening patterns that can be analyzed both qualitatively and quantitatively. This work improves our understanding of users' interactions with music and opens up avenues of research into user behavior and fostering diversity in recommender systems. A dataset of 2000 user histories tagged by genre over 17 months, supplied by Deezer (a leading music streaming company), is also released with the code.