Pulling strings from a tangle: visualizing a personal music listening history

ABSTRACT

The history of songs, to which a person has listened, is a very personal piece of information. It is a rich data set that comes as a byproduct of the use of digital music players and can be obtained without interfering with the user.

In this paper, we present three visualizations for this data set and a mechanism for generating new playlists from the user's own listening history, based on a navigation metaphor. First, temporal proximity is interpreted as a simple similarity measure to lay out the entire history on a two-dimensional plane. Closed listening sessions are then used to make chronological relations visible.

The generated playlists mimic the user's previous listening behavior, and the visualizations make the automatic choices understandable, as they share visual properties with the history. In this sense, our visualizations provide a visual vocabulary for listening behaviors and bring scrutability to automatic playlist generation.

REFERENCES

• 1: Andreja Andric , Goffredo Haus, Automatic playlist generation based on tracking user's listening habits, Multimedia Tools and Applications, v.29 n.2, p.127-151, June 2006 [doi>10.1007/s11042-006-0003-9]
• 2: J.-J. Aucouturier and F. Pachet. Improving timbre similarity: How high's the sky? Journal of Negative Results in Speech and Audio Sciences, 1(1), 2004.
• 3: Frank Bentley , Crysta Metcalf , Gunnar Harboe, Personal vs. commercial content: the similarities between consumer use of photos and music, Proceedings of the SIGCHI conference on Human Factors in computing systems, April 22-27, 2006, Montréal, Québec, Canada [doi>10.1145/1124772.1124871]
• 4: Hung-Chen Chen , Arbee L. P. Chen, A music recommendation system based on music data grouping and user interests, Proceedings of the tenth international conference on Information and knowledge management, October 05-10, 2001, Atlanta, Georgia, USA [doi>10.1145/502585.502625]
• 5: Matthew Cooper , Jonathan Foote , Andreas Girgensohn , Lynn Wilcox, Temporal event clustering for digital photo collections, ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP), v.1 n.3, p.269-288, August 2005 [doi>10.1145/1083314.1083317]
• 6: Judy Kay, Stereotypes, Student Models and Scrutability, Proceedings of the 5th International Conference on Intelligent Tutoring Systems, p.19-30, June 19-23, 2000
• 7: R. Lambiotte and M. Ausloos. Uncovering collective listening habits and music genres in bipartite networks. Physical review, 72(6), Dec. 2005.
• 8: E. Pampalk. Islands of music: Analysis, organization, and visualization of music archives. Technical report, Vienna University of Technology, 2001.
• 9: E. Pampalk, T. Pohle, and G. Widmer. Dynamic playlist generation based on skipping behaviour. In Proc. of the 6th ISMIR Conference, pages 634--637, 2005.
• 10: S. Pauws and B. Eggen. PATS: Realization and user evaluation of an automatic playlist generator. In Proceedings of the Third International Conference on Music Information Retrieval. Paris: IRCAM, pages 222--230, 2002.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.m Miscellaneous

General Terms:
Design, Human Factors

Keywords:
listening history, navigation metaphor, playlist creation, visualization