On Stakeholders and Data Biases in Music Recommendation

Time: Wed 2019-09-25 15.30 - 17.00

Lecturer: Peter Knees

Location: Seminarierum, 1440, E-huset

Title: On Stakeholders and Data Biases in Music Recommendation

Abstract: Music recommenders have become a commodity for music listeners. They drive manifold personalized services such as music discovery and activity-based playlisting. In practice, the task of music recommendation is a multi-faceted task, serving multiple stakeholders. Besides the music listener and the publishers of the music, the service itself as well as other branches of the music industry are affected. In this talk, I will discuss the multiple aspects and stakeholders present in the process of music recommendation. I will further discuss possible impacts on academic research in this area, foremost regarding the question of potential biases in datasets and illustrate aspects that should be taken into consideration when developing music recommender systems.

Bio: Peter Knees is an Assistant Professor of the Faculty of Informatics, TU Wien, Austria. He holds a Master degree in Computer Science from TU Wien and a PhD in the same field from Johannes Kepler University Linz, Austria. For over 15 years, he has been an active member of the Music Information Retrieval research community, reaching out to the related fields of multimedia and text information retrieval, recommender systems, and the digital arts.

His research activities center on music search engines and interfaces as well as music recommender systems, and more recently, on smart(er) tools for music creation.
Further information: www.ifs.tuwien.ac.at/~knees/

Page responsible:Web editors at EECS
Belongs to: Media Technology and Interaction Design
Last changed: Sep 20, 2019