Maximizing the Engagement: Exploring New Signals of Implicit Feedback in Music Recommendations

Music recommendation engines play a pivotal role in connecting artists with their listeners. Optimizing myopically only for user satisfaction may lead systems to recommend just a small fraction of all the available artists, or to recommend artists to users who might engage with them only in the short-term. In this work, we investigate such effects by exploring different signals of implicit feedback provided by users when using a music service (i.e., counting the number of tracks, days or times a user listens to an artist) and propose novel combined signals. Our approaches are evaluated over four different datasets, combining traditional user-centered evaluation metrics with artist-based ones, which allows us to measure the quality of the recommendations and the potential engagement with the recommended artists. Our experiments reveal that the selection of the implicit feedback signal has a significant impact on the quality of the recommendations. In addition, we show that the proposed signals increase the chances of a higher engagement between users and the artists they get recommended.

[1]  Lior Rokach,et al.  Introduction to Recommender Systems Handbook , 2011, Recommender Systems Handbook.

[2]  Friederike Wall,et al.  Agent-based modeling in managerial science: an illustrative survey and study , 2014, Review of Managerial Science.

[3]  Dietmar Jannach,et al.  Multistakeholder recommendation: Survey and research directions , 2020, User Modeling and User-Adapted Interaction.

[4]  Xavier Serra,et al.  Sound and Music Recommendation with Knowledge Graphs , 2016, ACM Trans. Intell. Syst. Technol..

[5]  Maria Soledad Pera,et al.  All The Cool Kids, How Do They Fit In?: Popularity and Demographic Biases in Recommender Evaluation and Effectiveness , 2018, FAT.

[6]  Eva Zangerle,et al.  #nowplaying Music Dataset: Extracting Listening Behavior from Twitter , 2014, WISMM '14.

[7]  Nazareno Andrade,et al.  A Multiobjective Music Recommendation Approach for Aspect-Based Diversification , 2017, ISMIR.

[8]  Jingjing Zhang,et al.  Consumption and Performance: Understanding Longitudinal Dynamics of Recommender Systems via an Agent-Based Simulation Framework , 2019, Inf. Syst. Res..

[9]  Robin Burke,et al.  Crank up the Volume: Preference Bias Amplification in Collaborative Recommendation , 2019, RMSE@RecSys.

[10]  Alexander Tuzhilin,et al.  The long tail of recommender systems and how to leverage it , 2008, RecSys '08.

[11]  Harald Steck,et al.  Item popularity and recommendation accuracy , 2011, RecSys '11.

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

[13]  Ichiro Fujinaga,et al.  Automatic Music Recommendation Systems: Do Demographic, Profiling, and Contextual Features Improve Their Performance? , 2016, ISMIR.

[14]  Katayoun Farrahi,et al.  Impact of Listening Behavior on Music Recommendation , 2014, ISMIR.

[15]  Andres Ferraro,et al.  Music cold-start and long-tail recommendation: bias in deep representations , 2019, RecSys.

[16]  Dietmar Jannach,et al.  Are we really making much progress? A worrying analysis of recent neural recommendation approaches , 2019, RecSys.

[17]  Noemi Mauro,et al.  Performance comparison of neural and non-neural approaches to session-based recommendation , 2019, RecSys.

[18]  Alejandro Bellogín,et al.  Precision-oriented evaluation of recommender systems: an algorithmic comparison , 2011, RecSys '11.

[19]  Dmitry Bogdanov,et al.  Artist and style exposure bias in collaborative filtering based music recommendations , 2019, ArXiv.

[20]  Dietmar Jannach,et al.  Recommending Based on Implicit Feedback , 2018, Social Information Access.

[21]  Markus Schedl,et al.  The LFM-1b Dataset for Music Retrieval and Recommendation , 2016, ICMR.

[22]  Mounia Lalmas,et al.  Jointly Leveraging Intent and Interaction Signals to Predict User Satisfaction with Slate Recommendations , 2019, WWW.

[23]  Roberto Pagano,et al.  30Music Listening and Playlists Dataset , 2015, RecSys Posters.

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