The role of recommendation devices of music streaming platforms on content consumption and user tastes is at the heart of an active debate. The quantitative state of the art often overlooks the existence of distinct attitudes and expectations towards guidance and, thus, of a priori distinct classes of users in this regard.

Focusing on two dimensions of content diversity, we demonstrate that there is no blanket answer to the intertwinement of recommendation and consumption: it depends on users, rather than the other way around. Besides, we distinguish the two main types of recommendation co-existing on music platforms –algorithmic and editorial– and show that they might correspond to opposite roles. We suggest to speak of filter niches rather than bubbles, and hint at further ramifications for the study and design of recommendation systems.

This paper has been accepted for publication in the proceedings of the 15th ACM Conference on Recommender Systems (RecSys 2021). It was selected among the Best Paper shortlist and received an honourable mention.