Detecting Fake Reviews using Machine learning techniques: a survey

The discovery of fake reviews is one of the major concerns for the E-commerce business-the Consumers on reviews before finalizing their choice for the product. The authenticity of online reviews is influential for e-commerce. Various companies are even filling spammers' pockets to post negative reviews for their rivals. Therefore, techniques for fake reviews detection have been explored in the past decade. On that account, this work provides a comprehensive survey of existing spam detection methods describing its features used for individual as well as group spam detection. A summary of the dataset for updates, products and reviewers. It also concludes the features to be considered while detecting a fake review. It discusses the issues and challenges faced while designing a fake review detection algorithm. In this paper, we aim to overview existing detection approaches in a systematic way, define key research issues, and articulate future research challenges and opportunities for reviewing spam detection. The existing techniques mainly emphasized over supervised machine learning, for which we require a labelled dataset that could work on real-world applications.