Using supervised learning to classify authentic and fake online reviews

• Main Authors: Banerjee, Snehasish, Chua, Alton Yeow Kuan, Kim, Jung-Jae
• Other Authors: Wee Kim Wee School of Communication and Information
• Format: Conference or Workshop Item
• Language: English
• Published: 2015
• Subjects: DRNTU::Library and information science::Libraries::Information systems; DRNTU::Social sciences::Communication::Communication theories and models
• Online Access: https://hdl.handle.net/10356/107209; http://hdl.handle.net/10220/25330; http://dx.doi.org/10.1145/2701126.2701130
• Institution: Nanyang Technological University

Before making a purchase, users are increasingly inclined to browse online reviews that are posted to share post-purchase experiences of products and services. However, not all reviews are necessarily authentic. Some entries could be fake yet written to appear authentic. Conceivably, authentic and fake reviews are not easy to differentiate. Hence, this paper uses supervised learning algorithms to analyze the extent to which authentic and fake reviews could be distinguished based on four linguistic clues, namely, understandability, level of details, writing style, and cognition indicators. The model performance was compared with two baselines. The results were generally promising.