Support the underground: characteristics of beyond-mainstream music listeners

Abstract

Music recommender systems have become an integral part of music streaming services such as Spotify and Last.fm to assist users navigating the extensive music collections offered by them. However, while music listeners interested in mainstream music are traditionally served well by music recommender systems, users interested in music beyond the mainstream (i.e., non-popular music) rarely receive relevant recommendations. In this paper, we study the characteristics of beyond-mainstream music and music listeners and analyze to what extent these characteristics impact the quality of music recommendations provided. Therefore, we create a novel dataset consisting of Last.fm listening histories of several thousand beyond-mainstream music listeners, which we enrich with additional metadata describing music tracks and music listeners. Our analysis of this dataset shows four subgroups within the group of beyond-mainstream music listeners that differ not only with respect to their preferred music but also with their demographic characteristics. Furthermore, we evaluate the quality of music recommendations that these subgroups are provided with four different recommendation algorithms where we find significant differences between the groups. Specifically, our results show a positive correlation between a subgroup’s openness towards music listened to by members of other subgroups and recommendation accuracy. We believe that our findings provide valuable insights for developing improved user models and recommendation approaches to better serve beyond-mainstream music listeners.

Analyzing Item Popularity Bias of Music Recommender Systems: Are Different Genders Equally Affected?

“…The authors use the delta-GAP metric in the domain of music recommendations, and find that the delta-GAP metric does not show a difference between "niche" and "mainstream" users. The reason for this could be that a group-based metric is not suitable for the complexity of music styles, as user groups can be quite diverse within themselves [11]. Zhu et al [20] address a related problem of item under-recommendation bias, expressing it with ranking-based statistical parity and ranking-based equal opportunity metrics.…”

Diversity by Design in Music Recommender Systems

“…Adversarial perspective: enhance the visibility of underrepresented opinions. 2016) Kunaver and Požrl (2017) negative impact valorising underground artists, as recently explored by Kowald et al (2021).…”

“…• Cosine similarity computed over the users' track genre distributions. LFM-BeyMS (Kowald et al, 2021), subset of LFM-1b (Schedl, 2016).…”

What Drives Readership? An Online Study on User Interface Types and Popularity Bias Mitigation in News Article Recommendations

“…Many recommender systems are affected by popularity bias, which leads to an overrepresentation of popular items in the recommendation lists. One potential issue of this is that unpopular items (i.e., so-called long-tail items) are recommended rarely [14,15]. The news article domain is an example where ignoring popularity bias could have a significant societal effect.…”