Modeling Musical Genre Trajectories through Pathlet Learning

TL;DR

This paper introduces a novel pathlet learning framework using dictionary learning to model and analyze the evolving musical genre preferences of users over time, providing interpretable trajectory embeddings.

Contribution

It proposes a new pathlet-based approach for modeling genre trajectories, enhancing understanding of user preferences and behavior in music streaming data.

Findings

Pathlet learning reveals meaningful listening patterns.

The framework produces interpretable trajectory embeddings.

The dataset and code are publicly released.

Abstract

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.