Do Recommender Systems Promote Local Music? A Reproducibility Study Using Music Streaming Data

TL;DR

This study reevaluates the impact of recommender systems on local music promotion using proprietary streaming data, revealing dataset-dependent biases and emphasizing the importance of reliable labeling for accurate conclusions.

Contribution

It provides a comparative analysis with proprietary data, highlights dataset and parameter influences on biases, and discusses challenges in local music labeling, promoting reproducibility.

Findings

Significant differences in local music consumption between datasets.

Recommender biases vary across datasets and model parameters.

Labeling local music is complex and can mislead conclusions.

Abstract

This paper examines the influence of recommender systems on local music representation, discussing prior findings from an empirical study on the LFM-2b public dataset. This prior study argued that different recommender systems exhibit algorithmic biases shifting music consumption either towards or against local content. However, LFM-2b users do not reflect the diverse audience of music streaming services. To assess the robustness of this study's conclusions, we conduct a comparative analysis using proprietary listening data from a global music streaming service, which we publicly release alongside this paper. We observe significant differences in local music consumption patterns between our dataset and LFM-2b, suggesting that caution should be exercised when drawing conclusions on local music based solely on LFM-2b. Moreover, we show that the algorithmic biases exhibited in the original work vary in our dataset, and that several unexplored model parameters can significantly influence these biases and affect the study's conclusion on both datasets. Finally, we discuss the complexity of accurately labeling local music, emphasizing the risk of misleading conclusions due to unreliable, biased, or incomplete labels. To encourage further research and ensure reproducibility, we have publicly shared our dataset and code.