Predicting helpful product reviews

Files in This Item:
File Description SizeFormat 
aics-2010b-crc.pdf337.59 kBAdobe PDFDownload
Title: Predicting helpful product reviews
Authors: O'Mahony, Michael P.
Cunningham, Pádraig
Smyth, Barry
Permanent link:
Date: 30-Aug-2010
Abstract: Millions of users are today posting user-generated content online, expressing their opinions on all manner of goods and services, topics and social affairs. While undoubtedly useful,user-generated content presents consumers with significant challenges in terms of information overload and quality considerations. In this paper, we address these issues in the context of product reviews and present a brief survey of our work to date on predicting review helpfulness. In particular, the performance of a variety of different machine learning approaches is evaluated on four large-scale review datasets drawn from the TripAdvisor and Amazon domains. Our findings highlight some interesting properties of this task from a machine learning perspective and demonstrate that author reputation, the sentiment expressed in reviews and review length are among the most effective predictors of review helpfulness.
Funding Details: Science Foundation Ireland
Type of material: Conference Publication
Keywords: User-generated contentProduct reviewsReview helpfulnessClassificationAmazonTripAdvisor
Subject LCSH: User-generated content--Evaluation
Recommender systems (Information filtering)
User-generated content--Classification
Language: en
Status of Item: Peer reviewed
Conference Details: Paper presented at the 21st Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2010), Galway, Ireland, 30 August - 1 September, 2010
Appears in Collections:CLARITY Research Collection
Computer Science Research Collection

Show full item record

Google ScholarTM


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.