IRLGSep 20, 2023

Popularity Degradation Bias in Local Music Recommendation

arXiv:2309.11671v12 citationsh-index: 1
Originality Synthesis-oriented
AI Analysis

This addresses the problem of popularity degradation bias in local music recommendations for users seeking diverse or long-tail artists, but it is incremental as it compares existing algorithms rather than introducing new ones.

The study examined how two top-performing recommendation algorithms, Weight Relevance Matrix Factorization (WRMF) and Multinomial Variational Autoencoder (Mult-VAE), perform in local music recommendations based on artist popularity, finding that both algorithms improve performance for more popular artists, exhibiting popularity degradation bias, with Mult-VAE showing better relative performance for less popular artists.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes