A Study on User Behavior Analysis with Graph-Structured Representations

He, Li

A Study on User Behavior Analysis with Graph-Structured Representations

He, Li

Permalink

Publication Type:: Thesis
Issue Date:: 2023

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (2.45 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	He, Li
dc.date.accessioned	2024-06-19T01:32:53Z
dc.date.available	2024-06-19T01:32:53Z
dc.date.issued	2023
dc.identifier.uri	http://hdl.handle.net/10453/179566
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	Nowadays, the development of Web 2.0 technology brings a huge change in the way of human's life styles. Variant e-commerce websites, e.g., Yelp, eBay and Amazon, provide internet user with a convenient, efficient and relatively reliable online trading environment. More and more merchants prefer to build their virtual shop through different online platforms. Meanwhile, an increasing number of consumers gradually get used to this way of shopping, and automatically share their shop experiences by using online platform which applied by the e-commerce website. This trend generates huge amount of user behavior information and product attributes during purchasing process. We define this online shopping scenario as a special kind of social network, named e-commerce Social Networks (ESNs) in this thesis. Online ESNs poses an interesting problem: how to best characterize the different classes of user behavior. Traditionally, user behavior representation methods, based on user individual features, are not appropriate for online networking platforms. In these complex social networks, users interact with other users through multiple interfaces that allow them to upload multimedia content and have many other interactions. Different behavior patterns can be observed for different individuals and groups. In this thesis, we will propose graph-structured methodologies for characterizing and identifying user behaviors in online social networks. This thesis will help the achievement of more strategic objectives on large-scale node classification tasks in graph-structured social network datasets.	en_US.UTF-8
dc.format	Thesis (PhD)
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/179566/1/thesis.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	© 2023 Li He
dc.rights	au.edu.uts.lib/cph
dc.title	A Study on User Behavior Analysis with Graph-Structured Representations	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

Nowadays, the development of Web 2.0 technology brings a huge change in the way of human's life styles. Variant e-commerce websites, e.g., Yelp, eBay and Amazon, provide internet user with a convenient, efficient and relatively reliable online trading environment. More and more merchants prefer to build their virtual shop through different online platforms. Meanwhile, an increasing number of consumers gradually get used to this way of shopping, and automatically share their shop experiences by using online platform which applied by the e-commerce website. This trend generates huge amount of user behavior information and product attributes during purchasing process. We define this online shopping scenario as a special kind of social network, named e-commerce Social Networks (ESNs) in this thesis. Online ESNs poses an interesting problem: how to best characterize the different classes of user behavior. Traditionally, user behavior representation methods, based on user individual features, are not appropriate for online networking platforms. In these complex social networks, users interact with other users through multiple interfaces that allow them to upload multimedia content and have many other interactions. Different behavior patterns can be observed for different individuals and groups. In this thesis, we will propose graph-structured methodologies for characterizing and identifying user behaviors in online social networks. This thesis will help the achievement of more strategic objectives on large-scale node classification tasks in graph-structured social network datasets.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/179566