Text mining and data information analysis for network public opinion

Abstract

Network public opinion information is massive and complex, and it is difficult to make effective use of manual means. In this paper, a method based on pattern matching and machine learning (PMML) was proposed to analyze the emotional tendencies of network public opinion. Firstly, the key words in public opinion were extracted, then the patterns were extracted and matched, and the emotional tendencies of words were calculated to obtain the pattern sequence vectors. Support vector machine (SVM) classifier was used to classify emotional tendencies. The Internet reviews of Meituan hotel were taken as the experimental subject. PMML method was found to have a high classification performance, with a maximum accuracy of 86.75%. It suggested the effectiveness of the proposed method. Then PMML method was used to classify the emotional tendencies of the collected reviews, and the results showed that the negative emotional tendency was greater than the positive tendency, which showed the inadequacy of Meituan hotel. The experiments in this paper provide some basis for the application of PMML in sentiment analysis of Internet public opinion.