A Correction Method of Online Product Scores from the Perspective of Discourse Markers Theory

摘要

Online product reviews is an important information source which affects consumer purchasing decision-making deeply, but the inconsistency between reviews and scores brings troubles in the process of decision-making for consumers. So the importance of solving reviews' authenticity is focused on. This paper attempts to introduce the Discourse Markers Theory to make a correction on review scores by analyzing the content of reviews, achieving a breakthrough in the semantic and pragmatic level. Firstly, we build a library of discourse markers in the field of online product reviews and design a correction system including credibility, position, emotional attitude. Then, we get the weight of each index through the questionnaire and propose a algorithm to correct deviation of reviews scores. In the last, the verification results from Jingdong mall show the method has better feasibility and validity.