Track Co-occurrence Analysis of Users' Music Listening History

Public Deposited
Analytics

Downloadable Content

Download PDF
Request Version for Screen Reader
Last Modified
  • February 28, 2019
Creator
  • Fan, Xueli
    • Affiliation: School of Information and Library Science
Abstract
  • Music services provide listeners access to great numbers of available tracks. It is time consuming for listeners to find potential favorite ones. Music listeners increasingly want playlists to be created automatically. This study examines the relationship between background knowledge about music and track co-occurrence frequency in users’ music listening history and builds a multiple linear regression model to predict the track co-occurrence. So given a seed track, the model can find out which track is most likely to co-occur. A simple objective evaluation compares predicted track with tracks in the users’ listening history. 13 out of 15 test tracks find the highest rank predicted track in the same listening history.
Date of publication
Subject
DOI
Resource type
Rights statement
  • In Copyright
Advisor
  • Shaw, Ryan
Degree
  • Master of Science in Information Science
Academic concentration
  • Library and Information Science
Degree granting institution
  • University of North Carolina at Chapel Hill
Graduation year
  • 2018
Language
Deposit record
  • 2422adb8-0919-4c37-9bc4-4f08f16dfa5d

Relations

Parents:

This work has no parents.

Items

Thumbnail Title Date Uploaded Visibility Actions
file details xuelifan.pdf 2019-05-14 Public Download
file details digitalmaterial_xuelifan.zip 2019-05-14 Public Download