Investigating gender fairness of recommendation algorithms in the music domain

作者：

Highlights：

• Novel large-scale real-world dataset of music listening records.

• Debiasing yields slight improvements of fairness recommendation algorithms.

• Formalizing and measuring the extent of compounding data biases by recommendation algorithms.

摘要

•Novel large-scale real-world dataset of music listening records.•Debiasing yields slight improvements of fairness recommendation algorithms.•Formalizing and measuring the extent of compounding data biases by recommendation algorithms.

论文关键词：Recommender systems,Music,Bias,Neural networks,Demographics

论文评审过程：Received 2 December 2020, Revised 28 April 2021, Accepted 16 June 2021, Available online 8 July 2021, Version of Record 8 July 2021.

论文官网地址：https://doi.org/10.1016/j.ipm.2021.102666