Towards online review spam detection

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

41 Scopus citations

Abstract

User reviews play a crucial role in Web, since many decisions are made based on them. However, review spam would misled the users, which is extremely obnoxious. In this poster, we explore the problem of online review spam detection. Firstly, we devise six features to find the spam based on the review content and re- viewer behaviors. Secondly, we apply supervised methods and an unsupervised one for spotting the review spam as early as possible. Finally, we carry out intensive experiments on a real-world review set to verify the proposed methods.

Original languageEnglish
Title of host publicationWWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web
PublisherAssociation for Computing Machinery, Inc
Pages341-342
Number of pages2
ISBN (Electronic)9781450327459
DOIs
StatePublished - 7 Apr 2014
Event23rd International Conference on World Wide Web, WWW 2014 - Seoul, Korea, Republic of
Duration: 7 Apr 201411 Apr 2014

Publication series

NameWWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web

Conference

Conference23rd International Conference on World Wide Web, WWW 2014
Country/TerritoryKorea, Republic of
CitySeoul
Period7/04/1411/04/14

Keywords

  • Online detection
  • Review analysis
  • Review spam

Fingerprint

Dive into the research topics of 'Towards online review spam detection'. Together they form a unique fingerprint.

Cite this