Identification of Fake Reviews Using New Set of Lexical and Syntactic Features
Rupesh Kumar Dewang, Anil Kumar Singh · 2015
The services and products of E-Commerce portals in this digital age are heavily reviewed by the users. These reviews provide useful insights on the quality/usage of these products. Due to such importance of reviews, they can be faked to give false opinions about products and subsequently mislead the users. In this paper we are proposing new set of lexical and syntactic features set and applying supervised algorithms for performing classification on fake reviews dataset (gold standard). We focus on the writing style, that include type of punctuation mark, Part-of- Speech (POS) etc., that are helpful for detection of reviews spam. The final results give promising accuracy 91.51% for detecting fake reviews.