Engaging with music retrieval

Boland, Daniel (2015) Engaging with music retrieval. PhD thesis, University of Glasgow.

Abstract

Music collections available to listeners have grown at a dramatic pace, now spanning tens of millions of tracks. Interacting with a music retrieval system can thus be overwhelming, with users offered ‘too-much-choice’. The level of engagement required for such retrieval interactions can be inappropriate, such as in mobile or multitasking contexts. Music recommender systems are widely employed to address this issue, however tend toward the opposite extreme of disempowering users and suffer from issues of subjectivity and confounds, such as the equalisation of tracks. This challenge and the styles of retrieval interaction involved are characterised in terms of user engagement in music retrieval, and the relationships between existing conceptualisations of user engagement is explored. Using listening histories and work from music psychology, a set of engagement-stratified profiles of listening behaviour are developed. A dataset comprising the playlists of thousands of users is used to contribute a user-centric approach to feature selection. The challenge of designing music retrieval for different levels of user engagement is first explored with a proof of concept, low engagement music retrieval system enabling users to casually retrieve music by tapping its rhythm as a query. The design methodology is then generalised with an engagement-dependent system, allowing users to denote their level of engagement and thus the specificity of their music queries. The engagement-dependent retrieval interaction is then explored as a component in a commercial music system. This thesis contributes the engagement-stratified profiles and metrics of listening behaviour, a corresponding design methodology for interaction, and presents a set of research and commercial applications for music retrieval.

• Item Type: Thesis (PhD)
• Qualification Level: Doctoral
• Keywords: music, information retrieval, MIR, engagement, UI, interfaces, users, information theory, recommendation, interaction, rhythm, playlist, subjectivity
• Subjects: Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science; Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources; Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4450 Databases
• Colleges/Schools: College of Science and Engineering > School of Computing Science
• Supervisor's Name: Murray-Smith, Professor Roderick
• Date of Award: 2015
• Depositing User: Mr Daniel Boland
• Unique ID: glathesis:2015-6727
• Copyright: Copyright of this thesis is held by the author.
• Date Deposited: 07 Oct 2015 08:34
• Last Modified: 28 Oct 2015 09:12
• URI: https://theses.gla.ac.uk/id/eprint/6727