Modeling Activity-Driven Music Listening with PACE

TL;DR

This paper introduces PACE, a framework for creating user embeddings based on periodic listening behaviors, revealing insights into user listening dynamics and improving activity prediction in music recommender systems.

Contribution

The paper presents PACE, a novel method for modeling user listening patterns using multichannel time-series data to enhance understanding of user habits.

Findings

Embeddings effectively capture repetitive listening behaviors.

PACE improves prediction of user activities during music listening.

User embeddings reveal detailed insights into listening habits.

Abstract

While the topic of listening context is widely studied in the literature of music recommender systems, the integration of regular user behavior is often omitted. In this paper, we propose PACE (PAttern-based user Consumption Embedding), a framework for building user embeddings that takes advantage of periodic listening behaviors. PACE leverages users' multichannel time-series consumption patterns to build understandable user vectors. We believe the embeddings learned with PACE unveil much about the repetitive nature of user listening dynamics. By applying this framework on long-term user histories, we evaluate the embeddings through a predictive task of activities performed while listening to music. The validation task's interest is two-fold, while it shows the relevance of our approach, it also offers an insightful way of understanding users' musical consumption habits.