START Conference Manager    

TopicSpam: a Topic-Model based approach for spam detection

Jiwei Li and Sujian Li

The 51st Annual Meeting of the Association for Computational Linguistics - Short Papers (ACL Short Papers 2013)
Sofia, Bulgaria, August 4-9, 2013


Product reviews are now widely used by individuals and organizations for decision making. Due to the reason of profit, people try to game the system by writing fake reviews to promote target products. Therefore the task of deceptive review detection, has been widely paid attention to. In this paper, we propose a novel approach based on LDA generative topic model for fake reviews detection. Our model can aptly detect the subtle differences between deceptive reviews and truthful reviews and achieves about 95% accuracy on review spam datasets, which largely outputs existing baselines.

START Conference Manager (V2.61.0 - Rev. 2792M)