Listening factors: a large-scale principal components analysis of long-term music listening histories

Authors:
Dominikus Baur;Jennifer Büttgen;Andreas Butz
Affiliations:
University of Munich, Munich, Germany;University of Munich, Munich, Munich, Germany;University of Munich, Munich, Germany
Venue:
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Year:
2012

Citing 6
Cited 0

Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions

IEEE Transactions on Knowledge and Data Engineering
Collaborative filtering with temporal dynamics

Communications of the ACM
Statistical models of music-listening sessions in social media

Proceedings of the 19th international conference on World wide web
Music Recommendation and Discovery: The Long Tail, Long Fail, and Long Play in the Digital Music Space

Music Recommendation and Discovery: The Long Tail, Long Fail, and Long Play in the Digital Music Space
Temporal Dynamics in Music Listening Behavior: A Case Study of Online Music Service

ICIS '10 Proceedings of the 2010 IEEE/ACIS 9th International Conference on Computer and Information Science
"I'll press play, but I won't listen": profile work in a music-focused social network service

Proceedings of the ACM 2011 conference on Computer supported cooperative work

Quantified Score

Hi-index	0.01

Visualization

Abstract

There are about as many strategies for listening to music as there are music enthusiasts. This makes learning about overarching patterns and similarities difficult. In this paper, we present an empirical analysis of long-term music listening histories from the last.fm web service. It gives insight into the most distinguishing factors in music listening behavior. Our sample contains 310 histories with up to six years duration and 48 associated variables describing various user and music characteristics. Using a principal components analysis, we aggregated these variables into 13 components and found several correlations between them. The analysis especially showed the impact of seasons and a listener's interest in novelty on music choice. Using this information, a sample of a user's listening history or even just demographical data could be used to create personalized interfaces and novel recommendation strategies. We close with derived design considerations for future music interfaces.