This work explores the relationship between Spotify users’ attributes and their public playlists, focusing on identifying recurring musical characteristics associated with users’ individual attributes like demographics, habits, or personality traits. The study involved 739 Spotify users and analyzed over 10,000 publicly shared playlists, discovering a deep connection between a user’s Spotify playlists and their real-life attributes. This led to the creation of predictive models for users’ attributes through a DeepSet application, providing new ways of understanding users’ music preferences and personal identities.
Publication date: 26 Jan 2024
Project Page: https://doi.org/XXXXXXX.XXXXXXX
Paper: https://arxiv.org/pdf/2401.14296
