Popularity Degradation Bias in Local Music Recommendation

2023/09/20 by Trainor, April, Turnbull, Douglas
#FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2309.11671

Abstract

In this paper, we study the effect of popularity degradation bias in the context of local music recommendations. Specifically, we examine how accurate two top-performing recommendation algorithms, Weight Relevance Matrix Factorization (WRMF) and Multinomial Variational Autoencoder (Mult-VAE), are at recommending artists as a function of artist popularity. We find that both algorithms improve recommendation performance for more popular artists and, as such, exhibit popularity degradation bias. While both algorithms produce a similar level of performance for more popular artists, Mult-VAE shows better relative performance for less popular artists. This suggests that this algorithm should be preferred for local (long-tail) music artist recommendation.

Related

• Evaluating Recommender System Algorithms for Generating Local Music Playlists
• The Unfairness of Popularity Bias in Music Recommendation: A\n Reproducibility Study
• Exploring Popularity Bias in Music Recommendation Models and Commercial Steaming Services
• Artist and style exposure bias in collaborative filtering based music recommendations
• Advancing Cultural Inclusivity: Optimizing Embedding Spaces for Balanced Music Recommendations