Khan, Shah NoorHerder, EelcoKaya, Diba2024-08-212024-08-212024https://dl.gi.de/handle/20.500.12116/44279Music recommendation systems are widely used to consume music. However, non-mainstream users often receive recommendations that do not align with their individual preferences. While the algorithmic aspects of these systems have been extensively studied, this paper focuses on understanding the user perspective and experience. For this purpose, we carried out a focus group based study with Turkish-origin users and Dutch users in the Netherlands who use music recommendation systems such as Spotify. The results show that the experiences expressed by the participants were consistent with the literature on how recommender systems perform for minority users. Particularly, we observed that most of these is- sues are related to the more generic popularity bias, which further underlines the need to improve the representation of users with non-mainstream music preferences.enhttp://purl.org/eprint/accessRights/RestrictedAccessText/Workshop Paper10.18420/muc2024-mci-ws11-141