Abstract: The current research on identification of product spam comments at home and abroad is discussed and the characteristics of the research methods, deficiencies and the development trend are summarized Fifty-four related literatures were retrieved and screened on CNKI and Web of Science by using the keywords of “fake review” and “review spam” Literature analysis is used to classify and analyze the literature The optimization and innovation of research on identification features and identification methods, as well as the differences of identification methods for different objects such as spam comments, spam reviewers are emphasized It is found that the methods current research used can be divided into content-based methods and methods based on the structure of comments, reviewers and commented products In the future research, effective identification features with multi-dimensions should be picked up and methods should be optimized according to the characteristics of data sets

Key words: online comment, spam comment identification, text mining, literature review