A network-based approach to detect spammer groups

Do, QNT; Zhilin, A; Junior, CZP; Wang, G; Hussain, FK

A network-based approach to detect spammer groups

Do, QNT Zhilin, A Junior, CZP Wang, G Hussain, FK

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings of the International Joint Conference on Neural Networks, 2016, 2016-October pp. 3642 - 3648
Issue Date:: 2016-10-31

Closed Access

	Filename	Description	Size
	07727668.pdf	Published version	1.11 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Do, QNT	en_US
dc.contributor.author	Zhilin, A	en_US
dc.contributor.author	Junior, CZP	en_US
dc.contributor.author	Wang, G	en_US
dc.contributor.author	Hussain, FK https://orcid.org/0000-0003-1513-8072	en_US
dc.date.issued	2016-10-31	en_US
dc.identifier.citation	Proceedings of the International Joint Conference on Neural Networks, 2016, 2016-October pp. 3642 - 3648	en_US
dc.identifier.isbn	9781509006199	en_US
dc.identifier.uri	http://hdl.handle.net/10453/98895
dc.description.abstract	© 2016 IEEE. Online reviews nowadays are an important source of information for consumers to evaluate online services and products before deciding which product and which provider to choose. Therefore, online reviews have significant power to influence consumers' purchase decisions. Being aware of this, an increasing number of companies have organized spammer review campaigns, in order to promote their products and gain an advantage over their competitors by manipulating and misleading consumers. To make sure the Internet remains a reliable source of information, we propose a method to identify both individual and group spamming reviews by assigning a suspicion score to each user. The proposed method is a network-based approach combining clustering techniques. We demonstrate the efficiency and effectiveness of our approach on a real-world and manipulated dataset that contains over 8000 restaurants and 600,000 restaurant reviews from TripAdvisor website. We tested our method in three testing scenarios. The method was able to detect all spammers in two testing scenarios, however it did not detect all in the last scenario.	en_US
dc.relation.ispartof	Proceedings of the International Joint Conference on Neural Networks	en_US
dc.relation.isbasedon	10.1109/IJCNN.2016.7727668	en_US
dc.title	A network-based approach to detect spammer groups	en_US
dc.type	Conference Proceeding
utslib.citation.volume	2016-October	en_US
utslib.for	080301 Bioinformatics Software	en_US
utslib.for	080109 Pattern Recognition and Data Mining	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
pubs.organisational-group	/University of Technology Sydney/Students
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US
pubs.volume	2016-October	en_US

Abstract:

© 2016 IEEE. Online reviews nowadays are an important source of information for consumers to evaluate online services and products before deciding which product and which provider to choose. Therefore, online reviews have significant power to influence consumers' purchase decisions. Being aware of this, an increasing number of companies have organized spammer review campaigns, in order to promote their products and gain an advantage over their competitors by manipulating and misleading consumers. To make sure the Internet remains a reliable source of information, we propose a method to identify both individual and group spamming reviews by assigning a suspicion score to each user. The proposed method is a network-based approach combining clustering techniques. We demonstrate the efficiency and effectiveness of our approach on a real-world and manipulated dataset that contains over 8000 restaurants and 600,000 restaurant reviews from TripAdvisor website. We tested our method in three testing scenarios. The method was able to detect all spammers in two testing scenarios, however it did not detect all in the last scenario.

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

http://hdl.handle.net/10453/98895