Tailoring Music Recommendations to Users by Considering Diversity, Mainstreaminess, and Novelty
Authors:
Open Access
- 9 August 2015
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 947-950
Abstract
A shortcoming of current approaches for music recommendation is that they consider user-specific characteristics only on a very simple level, typically as some kind of interaction between users and items when employing collaborative filtering. To alleviate this issue, we propose several user features that model aspects of the user's music listening behavior: diversity, mainstreaminess, and novelty of the user's music taste. To validate the proposed features, we conduct a comprehensive evaluation of a variety of music recommendation approaches (stand-alone and hybrids) on a collection of almost 200 million listening events gathered from \propername{Last.fm}. We report first results and highlight cases where our diversity, mainstreaminess, and novelty features can be beneficially integrated into music recommender systems.Keywords
Funding Information
- EU-FP7 (601166)
- Austrian Science Fund (FWF) (P25655)
This publication has 13 references indexed in Scilit:
- On the Influence of User Characteristics on Music Recommendation Algorithms2015
- Music Information Retrieval: Recent Developments and ApplicationsFoundations and Trends® in Information Retrieval, 2014
- Collaborative Filtering beyond the User-Item MatrixACM Computing Surveys, 2014
- Just-for-Me2014
- Location-aware music recommendation using auto-tagging and hybrid matching2013
- Context-aware mobile music recommendation for daily activities2012
- InCarMusic: Context-Aware Music Recommendations in a Car2011
- Context-Aware Recommender Systems2010
- A Context-Aware Music Recommendation System Using Fuzzy Bayesian Networks with Utility Theory2006
- Supervised term weighting for automated text categorization2003