Predicting user demographics from music listening information

The authors investigate to which extent the music listening habits of users of the social music platform Last.fm can be used to predict their age, gender, and nationality. They propose a feature modeling approach building on Term Frequency-Inverse Document Frequency (TF-IDF) for artist listening information and artist tags combined with additionally extracted features. Results show that we can substantially outperform a baseline majority voting approach and can compete with existing approaches. Further, regarding prediction accuracy vs. available listening data it is shows that even one single listening event per user is enough to outperform the baseline in all prediction tasks. The authors also compare the performance of our algorithm for different user groups and discuss possible prediction errors and how to mitigate them. Conclusion: personal information can be derived from music listening information, which indeed can help better tailoring recommendations, as it is illustrated with the use case of a music recommender system that can directly utilize the user attributes predicted by the algorithm to increase the quality of it’s recommendations.