Please use this identifier to cite or link to this item: https://hdl.handle.net/1959.11/61348
Full metadata record
DC FieldValueLanguage
dc.contributor.authorBudhi, Gregorius Satiaen
dc.contributor.authorChiong, Raymonden
dc.date.accessioned2024-07-10T00:58:48Z-
dc.date.available2024-07-10T00:58:48Z-
dc.date.issued2023-04-05-
dc.identifier.citationACM Transactions on Internet Technology, 23(1), p. 1-24en
dc.identifier.issn1557-6051en
dc.identifier.issn1533-5399en
dc.identifier.urihttps://hdl.handle.net/1959.11/61348-
dc.description.abstract<p>The financial impact of online reviews has prompted some fraudulent sellers to generate fake consumer reviews for either promoting their products or discrediting competing products. In this study, we propose a novel ensemble model—the <b>Multi-type Classifier Ensemble (MtCE)</b>—combined with a textual-based featuring method, which is relatively independent of the system, to detect fake online consumer reviews. Unlike other ensemble models that utilise only the same type of single classifier, our proposed ensemble utilises several customised machine learning classifiers (including deep learning models) as its base classifiers. The results of our experiments show that the MtCE can adequately detect fake reviews, and that it outperforms other single and ensemble methods in terms of accuracy and other measurements for all the relevant public datasets used in this study. Moreover, if set correctly, the parameters of MtCE, such as base-classifier types, the total number of base classifiers, bootstrap, and the method to vote on output (e.g., majority or priority), can further improve the performance of the proposed ensemble.</p>en
dc.languageenen
dc.publisherAssociation for Computing Machineryen
dc.relation.ispartofACM Transactions on Internet Technologyen
dc.titleA Multi-type Classifier Ensemble for Detecting Fake Reviews Through Textual-based Feature Extractionen
dc.typeJournal Articleen
dc.identifier.doi10.1145/3568676en
local.contributor.firstnameGregorius Satiaen
local.contributor.firstnameRaymonden
local.profile.schoolSchool of Science & Technologyen
local.profile.emailrchiong@une.edu.auen
local.output.categoryC1en
local.record.placeauen
local.record.institutionUniversity of New Englanden
local.publisher.placeUnited States of Americaen
local.identifier.runningnumber16en
local.format.startpage1en
local.format.endpage24en
local.peerreviewedYesen
local.identifier.volume23en
local.identifier.issue1en
local.contributor.lastnameBudhien
local.contributor.lastnameChiongen
dc.identifier.staffune-id:rchiongen
local.profile.orcid0000-0002-8285-1903en
local.profile.roleauthoren
local.profile.roleauthoren
local.identifier.unepublicationidune:1959.11/61348en
dc.identifier.academiclevelAcademicen
dc.identifier.academiclevelAcademicen
local.title.maintitleA Multi-type Classifier Ensemble for Detecting Fake Reviews Through Textual-based Feature Extractionen
local.output.categorydescriptionC1 Refereed Article in a Scholarly Journalen
local.search.authorBudhi, Gregorius Satiaen
local.search.authorChiong, Raymonden
local.uneassociationNoen
dc.date.presented2023-
local.atsiresearchNoen
local.sensitive.culturalNoen
local.year.published2023en
local.year.presented2023en
local.fileurl.closedpublishedhttps://rune.une.edu.au/web/retrieve/37188565-d44f-40d9-ae31-c632bd38aae9en
local.subject.for20204602 Artificial intelligenceen
local.profile.affiliationtypeExternal Affiliationen
local.profile.affiliationtypeExternal Affiliationen
local.date.moved2024-07-23en
Appears in Collections:Journal Article
School of Science and Technology
Files in This Item:
1 files
File SizeFormat 
Show simple item record

SCOPUSTM   
Citations

4
checked on Oct 26, 2024
Google Media

Google ScholarTM

Check

Altmetric


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