Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/151846
Title: EXPLOITING CROSS-CHANNEL INFORMATION FOR PERSONALIZED RECOMMENDATION
Authors: WANG XIANG
Keywords: Personalized Recommendation, Cross Channel, Social Recommendation, Explainable Recommendation, Knowledge-aware Recommendation, Auxiliary Data
Issue Date: 10-Aug-2018
Citation: WANG XIANG (2018-08-10). EXPLOITING CROSS-CHANNEL INFORMATION FOR PERSONALIZED RECOMMENDATION. ScholarBank@NUS Repository.
Abstract: Personalized recommendation is ubiquitous, having been applied to many online services such as E-commerce and advertise. In this thesis, we explore auxiliary information across different channels, such as user demographics, social relations, and item knowledge, to enrich the representations of users and items in performing better recommendation. In particular, a channel refers to one source which can indicate users' preferences towards an item. Consequently, cross-channel means incorporating multiple sources of information in establishing the whole view of user-item interactions. We investigate the role of cross-channel auxiliary information in various personalized recommendation scenarios --- leveraging user behaviors across online and offline channels for event recommendation, exploring social recommendation across information- and social-oriented channels, exploiting user-centric and item-centric channels for explainable recommendation, and knowledge-aware explanations.
URI: http://scholarbank.nus.edu.sg/handle/10635/151846
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
WangX.pdf5.77 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

9
checked on Apr 20, 2019

Download(s)

75
checked on Apr 20, 2019

Google ScholarTM

Check


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