Latent Feature Combination for Multi-Context Music Recommendation

In recent years, music aficionados have increasingly been consuming music via public music streaming platforms. Due to the size of the collections provided, music recommender systems have become a vital component as these aim to provide recommendations that match the user's current context as, throughout the day, users listen to music in numerous different contexts and situations. In this paper, we propose a multi-context-aware track recommender system that jointly exploits information about the current situation and musical preferences of users. To jointly model users by their situational and musical preferences, we cluster users based on their situational features and similarly, cluster music tracks based on their content features. Our experiments show that by relying on Factorization Machines for the computation of recommendations, the proposed approach allows to successfully leverage interaction effects between listening histories, situational and track content information, substantially outperforming a set of baseline recommenders.

[1]  Eva Zangerle,et al.  Towards a Context-Aware Music Recommendation Approach: What is Hidden in the Playlist Name? , 2015, 2015 IEEE International Conference on Data Mining Workshop (ICDMW).

[2]  Lars Schmidt-Thieme,et al.  BPR: Bayesian Personalized Ranking from Implicit Feedback , 2009, UAI.

[3]  Sally Jo Cunningham,et al.  'More of an Art than a Science': Supporting the Creation of Playlists and Mixes , 2006, ISMIR.

[4]  Gert R. G. Lanckriet,et al.  Learning Content Similarity for Music Recommendation , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[5]  Eva Zangerle,et al.  Understanding Playlist Creation on Music Streaming Platforms , 2016, 2016 IEEE International Symposium on Multimedia (ISM).

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

[7]  Eva Zangerle,et al.  Exploiting Twitter's Collective Knowledge for Music Recommendations , 2012, #MSM.

[8]  Yifan Hu,et al.  Collaborative Filtering for Implicit Feedback Datasets , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[9]  Qiang Yang,et al.  One-Class Collaborative Filtering , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[10]  Bernd Ludwig,et al.  InCarMusic: Context-Aware Music Recommendations in a Car , 2011, EC-Web.

[11]  Patrick Seemann,et al.  Matrix Factorization Techniques for Recommender Systems , 2014 .

[12]  Seungmin Rho,et al.  Music emotion classification and context-based music recommendation , 2010, Multimedia Tools and Applications.

[13]  Bernd Ludwig,et al.  Matrix factorization techniques for context aware recommendation , 2011, RecSys '11.

[14]  Francesco Ricci,et al.  Location-aware music recommendation using auto-tagging and hybrid matching , 2013, RecSys.

[15]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[16]  Steffen Rendle,et al.  Factorization Machines with libFM , 2012, TIST.

[17]  Jin Ha Lee,et al.  A Look at the Cloud from Both Sides Now: An Analysis of Cloud Music Service Usage , 2016, ISMIR.

[18]  Eva Zangerle,et al.  Improving Context-Aware Music Recommender Systems: Beyond the Pre-filtering Approach , 2017, ICMR.

[19]  Yehuda Koren,et al.  Factorization meets the neighborhood: a multifaceted collaborative filtering model , 2008, KDD.

[20]  Yehuda Koren,et al.  Collaborative filtering with temporal dynamics , 2009, KDD.

[21]  Katayoun Farrahi,et al.  User geospatial context for music recommendation in microblogs , 2014, SIGIR.

[22]  Mark P. Graus,et al.  Understanding choice overload in recommender systems , 2010, RecSys '10.

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

[24]  Nicholas J. Belkin,et al.  Categories of Music Description and Search Terms and Phrases Used by Non-Music Experts , 2002, ISMIR.

[25]  Tao Mei,et al.  Just-for-Me: An Adaptive Personalization System for Location-Aware Social Music Recommendation , 2014, ICMR.

[26]  J. Stephen Downie,et al.  Survey Of Music Information Needs, Uses, And Seeking Behaviours: Preliminary Findings , 2004, ISMIR.

[27]  Gediminas Adomavicius,et al.  Context-aware recommender systems , 2008, RecSys '08.