RESEARCH ARTICLE Global and country-specific mainstreaminess measures: Definitions, analysis, and usage for improving personalized music recommendation systems ☯ ☯ Christine BauerID *, Markus Schedl Institute of Computational Perception, Johannes Kepler University Linz, Linz, Austria a1111111111 ☯ These authors contributed equally to this work. a1111111111 *
[email protected] a1111111111 a1111111111 a1111111111 Abstract Relevance OPEN ACCESS Popularity-based approaches are widely adopted in music recommendation systems, both Citation: Bauer C, Schedl M (2019) Global and in industry and research. These approaches recommend to the target user what is currently country-specific mainstreaminess measures: popular among all users of the system. However, as the popularity distribution of music Definitions, analysis, and usage for improving items typically is a long-tail distribution, popularity-based approaches to music recommen- personalized music recommendation systems. PLoS ONE 14(6): e0217389. https://doi.org/ dation fall short in satisfying listeners that have specialized music preferences far away from 10.1371/journal.pone.0217389 the global music mainstream. Addressing this gap, the contribution of this article is three- Editor: Chi Ho Yeung, Education University of Hong fold. Kong, CHINA Received: August 28, 2018 Definition of mainstreaminess measures Accepted: May 12, 2019 First, we provide several quantitative measures describing the proximity of a user's music preference to the music mainstream. Assuming that there is a difference between the global Published: June 7, 2019 music mainstream and a country-specific one, we define the measures at two levels: relating Copyright: © 2019 Bauer, Schedl. This is an open a listener's music preferences to the global music preferences of all users, or relating them access article distributed under the terms of the Creative Commons Attribution License, which to music preferences of the user's country.