Oh, Behave! Country Representation Dynamics Created by Feedback Loops in Music Recommender Systems

TL;DR

This study investigates how feedback loops in music recommender systems influence the representation imbalance of local and US music, revealing that most models tend to reduce local music recommendations over time.

Contribution

The paper provides a simulation-based analysis of representation dynamics in music recommender systems, highlighting the impact of feedback loops on local music exposure.

Findings

Most models decrease local music recommendations over time.

Models maintaining average US and local music proportions do not ensure country-calibrated recommendations.

Popularity calibration does not necessarily improve country calibration.

Abstract

Recent work suggests that music recommender systems are prone to disproportionally frequent recommendations of music from countries more prominently represented in the training data, notably the US. However, it remains unclear to what extent feedback loops in music recommendation influence the dynamics of such imbalance. In this work, we investigate the dynamics of representation of local (i.e., country-specific) and US-produced music in user profiles and recommendations. To this end, we conduct a feedback loop simulation study using the standardized LFM-2b dataset. The results suggest that most of the investigated recommendation models decrease the proportion of music from local artists in their recommendations. Furthermore, we find that models preserving average proportions of US and local music do not necessarily provide country-calibrated recommendations. We also look into popularity calibration and, surprisingly, find that the most popularity-calibrated model in our study (ItemKNN) provides the least country-calibrated recommendations. In addition, users from less represented countries (e.g., Finland) are, in the long term, most affected by the under-representation of their local music in recommendations.