A vast amount of movie reviews encompass the preferences of a broad audience toward various aspects of film and television works,which can provide decision support for the production and promotion of film and television dramas.This paper pro-poses an analysis model for online comments on TV series:Python is used to crawl comments from media platforms.After data pre-processing and segmentation,the SVM method and LSTM method are used to perform sentiment analysis on short and long com-ment texts respectively.Statistical and visualization methods are used to study comment words,semantic network relationships,emotional tendency evolution,text content features,and geographical popularity distribution.Taking the police drama"The Knock-out"as an example for empirical analysis,the results show that the proposed model can reasonably reveal the overall evolution of emotional popularity,and discover preferences,behavioral patterns,and geographical features of audience comments.
维普
万方数据