Merging multiple criteria to identify suspicious reviews

DSpace/Manakin Repository

Show simple item record

dc.contributor.author Wu, Guangyu
dc.contributor.author Greene, Derek
dc.contributor.author Cunningham, Pádraig
dc.date.accessioned 2010-08-18T15:18:55Z
dc.date.available 2010-08-18T15:18:55Z
dc.date.copyright 2010 by the Association for Computing Machinery, Inc.
dc.date.issued 2010
dc.identifier.isbn 978-1-60558-906-0
dc.identifier.uri http://hdl.handle.net/10197/2403
dc.description ACM Recommender Systems 2010, Barcelona, September 26-30, 2010 en
dc.description.abstract Assessing the trustworthiness of reviews is a key issue for the maintainers of opinion sites such as TripAdvisor, given the rewards that can be derived from posting false or biased reviews. In this paper we present a number of criteria that might be indicative of suspicious reviews and evaluate alternative methods for integrating these criteria to produce a unified 'suspiciousness' ranking. The criteria derive from characteristics of the network of reviewers and also from analysis of the content and impact of reviews and ratings. The integration methods that are evaluated are singular value decomposition and the unsupervised hedge algorithm. These alternatives are evaluated in a user study on TripAdvisor reviews, where volunteers were asked to rate the suspiciousness of reviews that have been highlighted by the criteria. en
dc.description.sponsorship Science Foundation Ireland en
dc.description.uri Conference details en
dc.description.uri http://recsys.acm.org/2010/ en
dc.format.extent 251267 bytes
dc.format.mimetype application/pdf
dc.language.iso en en
dc.publisher ACM en
dc.relation.ispartof RecSys '10 : Proceedings of the fourth ACM conference on Recommender systems :September 26–30, 2010 Barcelona, Spain
dc.subject Machine learning en
dc.subject Network analysis en
dc.subject Anomalous structure detection en
dc.subject.lcsh User-generated content--Evaluation en
dc.subject.lcsh Recommender systems (Information filtering)--Evaluation en
dc.subject.lcsh Machine learning
dc.subject.lcsh Communication--Network analysis
dc.title Merging multiple criteria to identify suspicious reviews en
dc.type Conference Publication en
dc.internal.availability Full text available en
dc.internal.webversions Publisher's version
dc.internal.webversions http://dx.doi.org/10.1145/1864708.1864757
dc.status Peer reviewed en
dc.neeo.contributor Wu|Guangyu|aut| en
dc.neeo.contributor Greene|Derek|aut| en
dc.neeo.contributor Cunningham|Pádraig|aut| en
dc.description.admin Check from Oct 2010 for publications details; if/when published, notify AV as copyright set phrase needs to be added to PDF with complete citation - AV 13/07/2010 ti, ke - TS 28/07/10 en


Files in this item

This item appears in the following Collection(s)

Show simple item record

This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.

If you are a publisher or author and have copyright concerns for any item, please email research.repository@ucd.ie and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.

Search Research Repository


Advanced Search

Browse