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 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.
Citation
Oleg
Lesota,
Jonas
Geiger,
Max Walder,
Dominik Kowald,
Markus
Schedl
Oh, Behave! Country Representation Dynamics Created by Feedback Loops in Music Recommender Systems
Proceedings of the 18th ACM Conference on Recommender Systems (RecSys), 2024.
BibTeX
@inproceedings{Lesota2024feedbackloops,
title = {Oh, Behave! Country Representation Dynamics Created by Feedback Loops in Music Recommender Systems},
author = {Lesota, Oleg and Geiger, Jonas and Walder, Max and Kowald, Dominik and Schedl, Markus},
booktitle = {Proceedings of the 18th ACM Conference on Recommender Systems (RecSys)},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
location = {Bari, Italy},
year = {2024}
}