Biases in Automated Music Playlist Generation: A Comparison of Next-Track Recommending Techniques

Playlist generation is a special form of music recommendation where the problem is to create a sequence of tracks to be played next, given a number of seed tracks. In academia, the evaluation of playlisting techniques is often done by assessing with the help of information retrieval measures if an algorithm is capable of selecting those tracks that also a human would pick next. Such approaches however cannot capture other factors, e.g., the homogeneity of the tracks that can determine the quality perception of playlists. In this work, we report the results of a multi-metric comparison of different academic approaches and a commercial playlisting service. Our results show that all tested techniques generate playlists with certain biases, e.g., towards very popular tracks, and often create playlists continuations that are quite different from those that are created by real users.

[1]  Malcolm Slaney,et al.  Measuring playlist diversity for recommendation systems , 2006, AMCMM '06.

[2]  Wietse Balkema,et al.  Music playlist generation by assimilating GMMs into SOMs , 2010, Pattern Recognit. Lett..

[3]  Paul Lamere.  I've got 10 million songs in my pocket: now what? , 2012, RecSys '12.

[4]  Francesco Ricci,et al.  Contextual music information retrieval and recommendation: State of the art and challenges , 2012, Comput. Sci. Rev..

[5]  Dan Barry,et al.  Interacting with large music collections: Towards the use of environmental metadata , 2008, 2008 IEEE International Conference on Multimedia and Expo.

[6]  George Karypis,et al.  A Comprehensive Survey of Neighborhood-based Recommendation Methods , 2011, Recommender Systems Handbook.

[7]  Dietmar Jannach,et al.  Automated Generation of Music Playlists: Survey and Experiments , 2014, ACM Comput. Surv..

[8]  Sun Park,et al.  Novel Recommendation Based on Personal Popularity Tendency , 2011, 2011 IEEE 11th International Conference on Data Mining.

[9]  John C. Platt,et al.  Learning a Gaussian Process Prior for Automatically Generating Music Playlists , 2001, NIPS.

[10]  Thorsten Joachims,et al.  Playlist prediction via metric embedding , 2012, KDD.

[11]  Jun Wang,et al.  Optimizing multiple objectives in collaborative filtering , 2010, RecSys '10.

[12]  Andy M. Sarroff.  MODELING AND PREDICTING SONG ADJACENCIES IN COMMERCIAL ALBUMS , 2012 .

[13]  Andreja Andric,et al.  Automatic playlist generation based on tracking user’s listening habits , 2006, Multimedia Tools and Applications.

[14]  Gert R. G. Lanckriet,et al.  Hypergraph Models of Playlist Dialects , 2012, ISMIR.

[15]  Dietmar Jannach,et al.  What recommenders recommend: an analysis of recommendation biases and possible countermeasures , 2015, User Modeling and User-Adapted Interaction.

[16]  Torsten Möller,et al.  A Survey on Music Listening and Management Behaviours , 2012, ISMIR.

[17]  Dietmar Jannach,et al.  Beyond "Hitting the Hits": Generating Coherent Music Playlist Continuations with the Right Tracks , 2015, RecSys.

[18]  Gert R. G. Lanckriet,et al.  The Natural Language of Playlists , 2011, ISMIR.

[19]  Lie Lu,et al.  Learning a music similarity measure on automatic annotations with application to playlist generation , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[20]  D. Jannach,et al.  EVALUATING THE QUALITY OF PLAYLISTS BASED ON HAND-CRAFTED SAMPLES , 2013 .

[21]  Jarno Seppänen,et al.  Evaluation of automatic mobile playlist generator , 2007, Mobility '07.

[22]  Dietmar Jannach,et al.  Evaluating The Quality of Generated Playlists Based on Hand-Crafted Samples , 2013, ISMIR.

[23]  Robin Burke,et al.  Context-aware music recommendation based on latenttopic sequential patterns , 2012, RecSys.

[24]  François Pachet,et al.  Scaling up music playlist generation , 2002, Proceedings. IEEE International Conference on Multimedia and Expo.

[25]  Alexander Tuzhilin,et al.  On over-specialization and concentration bias of recommendations: probabilistic neighborhood selection in collaborative filtering systems , 2014, RecSys '14.

[26]  Sahin Albayrak,et al.  A 3D approach to recommender system evaluation , 2013, CSCW '13.

[27]  Beth Logan,et al.  Content-Based Playlist Generation: Exploratory Experiments , 2002, ISMIR.