Research on Microblog Comment Clustering Algorithm Based on Emotional Topic Feature Word Weighting

In order to improve the effect of sentiment analysis clustering on microblog comments, this paper proposes a microblog comment clustering algorithm based on the weighted sentiment topic feature words. By defining the emotional-themed word bag, we can make full use of the emotional information contained in micro-blog comments. On this basis, by weighting emotion theme feature words, this paper makes full use of the theme features among microblog comments, considers the contribution of emotion theme words to the theme, and finally obtains weighted emotion theme feature words through LDA clustering. The research results show that the algorithm has a good clustering effect for sentiment analysis and is helpful to network public opinion analysis.