Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/49165
Title: Community Learning in Location-based Social Networks
Authors: ZHAO YILIANG
Keywords: Location-based Social Networks, Heterogeneous Hypergraph, Community Detection, Community Profiling, Social Dimensions, Cross Region Community Matching
Issue Date: 20-Sep-2013
Source: ZHAO YILIANG (2013-09-20). Community Learning in Location-based Social Networks. ScholarBank@NUS Repository.
Abstract: In recent years we have witnessed a flourish of location-based social media, such as Foursquare, Gowalla, Facebook Place, etc, which are collectively termed as location-based social networks (LBSNs). These services offer more location-tagged information to people, helping them to make better informed decisions on where to eat, sleep, shop and relax within the local context. The boom of LBSNs opens up a vast range of possibilities to study location-oriented human interactions and collective behaviours in an unprecedented scale. In this thesis, we propose a community learning framework in LBSNs to first detect and understand user communities based on the heterogeneous interactions in LBSNs. We next study community matching across geographical regions in the context of generating personalized recommendations of locally interesting venues to tourists. We have sampled a large-scale, representative and real world dataset from Foursquare and performed extensive experiments to verify the effectiveness of the proposed approaches.
URI: http://scholarbank.nus.edu.sg/handle/10635/49165
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
01ZhaoYL.pdf897 kBAdobe PDF

OPEN

NoneView/Download
02ZhaoYL.pdf7.94 MBAdobe PDF

OPEN

NoneView/Download
03ZhaoYL.pdf5.3 MBAdobe PDF

OPEN

NoneView/Download
04ZhaoYL.pdf7.67 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

300
checked on Feb 16, 2018

Download(s)

815
checked on Feb 16, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.