Are music streaming services’ recommendation algorithms biased towards male artists? It’s a question that has been raised before: most notably in The Baffler’s Spotify-focused ‘Discover Weakly’ analysis in 2018.
Now a new study from researchers at Universitat Pompeu Fabra in Spain and Utrecht University in the Netherlands has returned to the topic, analysing “gender imbalance in music recommenders” using public datasets from Last·fm.
You can read the full study here, and its authors have also published a summary on The Conversation. “Our analysis of around 330,000 users’ listening behaviour over nine years showed a clear picture – only 25% of the artists ever listened to were female,” they explained.
Meanwhile, when testing a popular algorithm used for music recommendations (the ‘alternating least square’ [ALS] algorithm) they found that “on average, the first recommended track was by a man, along with the next six. Users had to wait until song seven or eight to hear one by a woman”.
The concern being that this creates a feedback loop where more and more male artists might be recommended. The researchers also tested ways to break that feedback loop, and suggested that it is relatively simple to do.
Music Ally’s next Learn Live webinar will help you understand what’s required for artists to thrive in new international markets!