The first joint paper with Karlijn Dinnissen has just appeared in the journal Frontiers in Big Data. In this mini review, we take a stakeholder-centered view and discuss literature on fairness in music recommender systems from the perspective of the various stakeholders.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Music recommendation algorithms are unfair to female artists, but we can change that.

Article written by: Christine Bauer, Utrecht University and Andrés Ferraro, Universitat Pompeu Fabra

Andrés Ferraro will present our joint paper at CHIIR 2021. In the paper with the title Break the Loop: Gender Imbalance in Music Recommenders, we investigate the imbalance in music recommendations with respect to the artists gender. We propose a simple re-ranking approach to mitigate the problem and show in a simulation of feedback loops how the gender (im-)balances evolves over time.

I am glad that my summary of the ISMIR 2020 special session: ‘‘How do we—in MIR research—help artists? Do we?’’ made it to the December 2020 issue of the ACM SIGIR Forum.

While CHIIR 2020 had to be cancelled due to the current global situation with Covid-19, the paper accompanying the tutorial on multi-method evaluation (that I would have held there) is published.

I proudly present the PLOS ONE article by Markus Schedl and me: We analyze music preferences in 47 countries with respect to what is considered mainstream in a particular country. And, of course, we evaluate recommendation approaches considering users’ mainstreaminess.

I am proud to announce that my position paper on ‘‘The Potential of the Confluence of Theoretical and Algorithmic Modeling in Music Recommendation’’ has been accepted for the ACM CHI 2019 Workshop on Computational Modeling in Human-Computer Interaction (CompHCI 2019).