Artist and style exposure bias in collaborative filtering based music recommendations

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Ferraro, Andrés
• dc.contributor.author Bogdanov, Dmitry
• dc.contributor.author Serra, Xavier
• dc.contributor.author Yoon, Jason
• dc.date.accessioned 2020-04-14T10:23:57Z
• dc.date.available 2020-04-14T10:23:57Z
• dc.date.issued 2019
• dc.description Comunicació presentada a: The 1st Workshop on Designing Human-Centric MIR Systems, esdeveniment satèl·lit d'ISMIR 2019, celebrat a Delft, Holanda, el dia 2 de novembre de 2019.
• dc.description.abstract Algorithms have an increasing influence on the music that we consume and understanding their behavior is fundamental to make sure they give a fair exposure to all artists across different styles. In this on-going work we contribute to this research direction analyzing the impact of collaborative filtering recommendations from the perspective of artist and music style exposure given by the system. We first analyze the distribution of the recommendations considering the exposure of different styles or genres and compare it to the users’ listening behavior. This comparison suggests that the system is reinforcing the popularity of the items. Then, we simulate the effect of the system in the long term with a feedback loop. From this simulation we can see how the system gives less opportunity to the majority of artists, concentrating the users on fewer items. The results of our analysis demonstrate the need for a better evaluation methodology for current music recommendation algorithms, not only limited to user-focused relevance metrics.en
• dc.description.sponsorship This research has been supported by Kakao Corp.
• dc.format.mimetype application/pdf
• dc.identifier.citation Ferraro A, Bogdanov D, Serra S, Yoon J. Artist and style exposure bias in collaborative filtering based music recommendations. In: Miron M. Proceedings of the 1st Workshop on Designing Human-Centric MIR Systems; 2019 Nov 2; Delft, The Netherlands. [Delft]: ACM FAT Network; 2019. p. 8-10.
• dc.identifier.uri http://hdl.handle.net/10230/44211
• dc.language.iso eng
• dc.publisher ACM FAT Network
• dc.relation.ispartof Miron M. Proceedings of the 1st Workshop on Designing Human-Centric MIR Systems; 2019 Nov 2; Delft, The Netherlands. [Delft]: [ACM FAT* Network]; 2019. p. 8-10.
• dc.rights Andres Ferraro, Dmitry Bogdanov, Xavier Serra, Jason Yoon. Licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). Attribution: Andres Ferraro, Dmitry Bogdanov, Xavier Serra, Jason Yoon. “Artist and style exposure bias in collaborative filtering based music recommendations”, 20th International Society for Music Information Retrieval Conference, Delft, The Netherlands, 2019.
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri https://creativecommons.org/licenses/by/4.0/
• dc.subject.keyword Music recommendationen
• dc.subject.keyword Popularity biasen
• dc.subject.keyword Feedback loopsen
• dc.subject.keyword Simulationen
• dc.subject.keyword Fairnessen
• dc.title Artist and style exposure bias in collaborative filtering based music recommendations
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/publishedVersion