METHOD FOR PERFORMING FINE-GRAINED TEXT SENTIMENT ANALYSIS ON BASIS OF DEGREE OF USER DISSATISFACTION

摘要

A method for performing fine-grained text sentiment analysis on the basis of the degree of user dissatisfaction. According to the method, product attributes are automatically extracted according to comments in a data set, and the comments are segmented according to the product attributes, so as to achieve the effect of fine-grained analysis. Then, an analysis model, which takes degrees of user dissatisfaction into consideration, is used, and the analysis model takes the degrees of user dissatisfaction as hidden variables and solves same by means of an expectation-maximization (EM) algorithm, so as to obtain evaluation results of several product attributes of each product, thereby further improving the accuracy of sentiment analysis. According to the method, the problems in sentiment analysis of analysis granularity being too large and the degrees of user dissatisfaction differing are solved, such that high-quality sentiment analysis can be performed on product comments.