Effects of personal characteristics in control-oriented user interfaces for music recommender systems

Yucheng Jin*, Nava Tintarev, Nyi Nyi Htun, Katrien Verbert

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

27 Citations (Scopus)
187 Downloads (Pure)

Abstract

Music recommender systems typically offer a “one-size-fits-all” approach with the same user controls and visualizations for all users. However, the effectiveness of interactive interfaces for music recommender systems is likely to be affected by individual differences. In this paper, we first conduct a comprehensive literature review of interactive interfaces in recommender systems to motivate the need for personalized interaction with music recommender systems, and two personal characteristics, visual memory and musical sophistication. More specifically, we studied the influence of these characteristics on the design of (a) visualizations for enhancing recommendation diversity and (b) the optimal level of user controls while minimizing cognitive load. The results of three experiments show a benefit for personalizing both visualization and control elements to musical sophistication. We found that (1) musical sophistication influenced the acceptance of recommendations for user controls. (2) musical sophistication also influenced recommendation acceptance, and perceived diversity for visualizations and the UI combining user controls and visualizations. However, musical sophistication only strengthens the impact of UI on perceived diversity (moderation effect) when studying the combined effect of controls and visualizations. These results allow us to extend the model for personalization in music recommender systems by providing guidelines for interactive visualization design for music recommender systems, with regard to both visualizations and user control.

Original languageEnglish
Pages (from-to)199-249
Number of pages51
JournalUser Modeling and User-Adapted Interaction
Volume30 (2020)
Issue number2
DOIs
Publication statusPublished - 2019

Keywords

  • Acceptance
  • Cognitive load
  • Perceived diversity
  • Personal characteristics
  • Recommender systems
  • User control
  • User experience

Fingerprint

Dive into the research topics of 'Effects of personal characteristics in control-oriented user interfaces for music recommender systems'. Together they form a unique fingerprint.

Cite this