Predicting User Preference Based on Matrix Factorization by Exploiting Music Attributes

• Type: Article in International Conference Proceedings Book
• Date: 2016

Authors

Nabizadeh, AH (Author) Other; Jorge, AM (Author) FCUP; Tang, S (Author) Other; Yu, Y (Author) Other

Conference proceedings International

Title: ACM International Conference Proceeding Series

Pages: 61-66

9th International C* Conference on Computer Science and Software Engineering, C3S2E 2016

20 July 2016 through 22 July 2016

Indexing

Scopus - 10 Citations

Other information

Authenticus ID: P-00K-S9J

DOI: 10.1145/2948992.2949010

Abstract (EN): With the emergence of online Music Streaming Services (MSS) such as Pandora and Spotify, listening to music online became very popular. Despite the availability of these services, users face the problem of finding among millions of music tracks the ones that match their music taste. MSS platforms generate interaction data such as users' defined playlists enriched with relevant metadata. These metadata can be used to predict users' preferences and facilitate personalized music recommendation. In this work, we aim to infer music tastes of users by using personal playlist information. Characterizing users' taste is important to generate trustable recommendations when the amount of usage data is limited. Here, we propose to predict the users' preferred music feature's value (e.g. Genre as a feature has different values like P op, Rock, etc.) by modeling, not only usage information, but also music description features. Music attribute information and usage data are typically dealt with separately. Our method FPMF (Feature Prediction based on Matrix Factorization) treats music feature values as virtual users and retrieves the preferred feature values for real target users. Experimental results indicate that our proposal is able to handle the item cold start problem and can retrieve preferred music feature values with limited usage data. Furthermore, our proposal can be useful in recommendation explanation scenarios. © 2016 ACM.

Language: English

Type (Professor's evaluation): Scientific