Utilizing Context for Novel Point of Interest Recommendation
Loading...
Date
Author
Institution
University of Alberta
Degree Level
Master's
Degree
Master of Science
Department
Department of Electrical and Computer Engineering
Specialization
Software Engineering and Intelligent Systems
Supervisor / Co-Supervisor and Their Department(s)
Examining Committee Member(s) and Their Department(s)
Citation for Previous Publication
Link to Related Item
Abstract
Recommender systems are a modern solution for suggesting new items to users. One of their uses is for novel point of interest recommendation, recommending locations to a user which they have not visited. This can be applied to a location-based social network, which contains information about their users' travel history and social connections. Within this context, there are various challenges, such as data sparsity, that limit recommendation effectiveness. We propose an algorithm for personalized novel point of interest recommendation to overcome these challenges. Our solution leverages social, temporal, and spatial context, together with collaborative filtering and a classification algorithm.
Item Type
http://purl.org/coar/resource_type/c_46ec
Alternative
License
Other License Text / Link
This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.
Language
en