Interview with Christine Bauer at Science Notes
Image credit: Vimeo-Free-Videos from Pixabay, edited with pixelCrash® v1.1 by @van_der_exChristine Bauer was interviewed by Science Notes about what ‘fairness’ really means in music recommender systems, how powerful algorithms quietly decide which artists get heard and which stay invisible on digital music platforms.
In the interview, she explains how music recommender systems may not just reflect the inequalities in the music industry—they amplify them. The article highlights that women and gender minorities remain underrepresented in streaming recommendations and algorithmic feedback loops lock this imbalance in.
The interview also highlights that fairness in music recommendation can mean different things to artists, listeners, and streaming platforms.
Key topics discussed
- Recommendation algorithms can reinforce existing visibility patterns in the music industry.
- Tracks by women usually appear later in recommendation lists than tracks by men.
- Feedback loops in recommender systems may perpetuate existing gender imbalances over time.
- Computational simulations suggest that algorithmic changes can make music recommendations more balanced, giving a fairer share of visibility across artists.
- Research results suggest that how we rank recommendations has a far bigger impact on fairness outcomes than how users are simulated to choose among them.
- Different groups may have different perspectives on what fair recommendations mean. Hence, there is no single definition of fairness in music recommendation.
Video introduction to the article by Sophie Straetemans (Science Notes) on Instagram
Learn more
- Science Notes interview (in German): https://sciencenotes.de/gender-algorithmus-fairness/
- The interview is part of the article collection “Greatest Hits” on Science Notes, May 2026 (in German): https://sciencenotes.de/gender-algorithmus-fairness/
- Instagram reel by Sophie Straetemans introducing the article (in German)
- Spotify playlist accompanying the article (Science Notes editor team’s choice)
(2024).
It's not you, it's me: the impact of choice models and ranking strategies on gender imbalance in music recommendation.
18th ACM Conference on Recommender Systems (RecSys 2024).
