Detecting Fake Amazon Book Reviews using Rhetorical Structure Theory
نویسندگان
چکیده
This study explores the potential of a theory of discourse coherence relations to distinguish between truth and deception. It uses Rhetorical Structure Theory and logistic regression to build a deception model that achieves 78% accuracy on a sample of goldstandard Amazon book reviews drawn from the Deceptive Review corpus. It finds Contrast discourse relations to be a significant predictor of veracity and successfully tests a discourse mining method for their semi-automated extraction. These preliminary findings contribute to the development of a linguistic-based theory that can guide the design of computer-aided deception detection systems.
منابع مشابه
Fake Review Detection: Classification and Analysis of Real and Pseudo Reviews
In recent years, fake review detection has attracted significant attention from both businesses and the research community. For reviews to reflect genuine user experiences and opinions, detecting fake reviews is an important problem. Supervised learning has been one of the main approaches for solving the problem. However, obtaining labeled fake reviews for training is difficult because it is ve...
متن کاملWhat Yelp Fake Review Filter Might Be Doing?
Online reviews have become a valuable resource for decision making. However, its usefulness brings forth a curse ‒ deceptive opinion spam. In recent years, fake review detection has attracted significant attention. However, most review sites still do not publicly filter fake reviews. Yelp is an exception which has been filtering reviews over the past few years. However, Yelp’s algorithm is trad...
متن کاملRhetorical Structure Analysis of EFLs’ Written Narratives of a Picture Story
This study was set to reveal how second language learners use rhetorical relations in their written narratives in terms of Rhetorical Structure Theory (RST) primarily proposed by Mann & Thompson (1987) and developed by Mann, Matthiessen & Thompson (1992). To this end, sixty written narratives based on the picture story book ‘Frog, where are you?’ were collected from EFL learners and were put to...
متن کاملIdentifying fake Amazon reviews as learning from crowds
Customers who buy products such as books online often rely on other customers reviews more than on reviews found on specialist magazines. Unfortunately the confidence in such reviews is often misplaced due to the explosion of so-called sock puppetry–authors writing glowing reviews of their own books. Identifying such deceptive reviews is not easy. The first contribution of our work is the creat...
متن کاملSpotting Fake Reviews using Positive-Unlabeled Learning
Fake review detection has been studied by researchers for several years. However, so far all reported studies are based on English reviews. This paper reports a study of detecting fake reviews in Chinese. Our review dataset is from the Chinese review hosting site Dianping, which has built a fake review detection system. They are confident that their algorithm has a very high precision, but they...
متن کامل