O'Mahony, Michael P.Michael P.O'MahonySmyth, BarryBarrySmyth2010-09-282010-09-282010 Centr2010-04-28http://hdl.handle.net/10197/2463Paper presented at RIAO 2010 the 9th international conference on Adaptivity, Personalization and Fusion of Heterogeneous Information, Paris, France, April 28-30, 2010User-generated content provides online consumers with a wealth of information. Given the ever-increasing quantity of available content and the lack of quality control applied to this content, there is a clear need to enhance the user experience when it comes to effectively leveraging this vast information source. In this paper, we address these issues in the context of user-generated product reviews. We expand on recent work to consider the performance of structural and readability feature sets on the classification of helpful product reviews. Our findings, based on a large-scale evaluation of TripAdvisor and Amazon reviews, indicate that structural and readability features are useful predictors for Amazon product reviews but less so for TripAdvisor hotel reviews.216266 bytesapplication/pdfenUser-generated product reviewsClassificationHelpfulTripAdvisorAmazonUser-generated content--EvaluationUser-generated content--ClassificationReadability (Literary style)Recommender systems (Information filtering)Conference Publicationhttps://creativecommons.org/licenses/by-nc-sa/1.0/