Popularity Degradation Bias in Local Music Recommendation

TL;DR

This paper investigates how popular music recommendation algorithms tend to favor popular artists, revealing a bias that affects less popular artists and suggesting that Mult-VAE performs better for long-tail recommendations.

Contribution

The study identifies popularity degradation bias in top recommendation algorithms and compares their effectiveness across artist popularity levels, highlighting Mult-VAE's advantages for less popular artists.

Findings

Both algorithms favor popular artists, showing bias.

Mult-VAE outperforms WRMF for less popular artists.

Recommendation performance varies with artist popularity.

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.