Emotion analysis method for Douban network movie comments

Abstract

The invention relates to an emotion analysis method for Douban network movie comments, which is mainly used for carrying out emotion analysis on Chinese movie comments on the Douban network, and comprises the following steps of: firstly, carrying out data crawling operation on the movie comments on the Douban network, and then carrying out preprocessing operation on the data, including deleting stop words, segmenting words and tagging part of speech; secondly, constructing four types of dictionaries required for movie comment sentiment analysis, wherein the four types of dictionaries are respectively a basic sentiment dictionary, a negative word dictionary, a degree adverb dictionary and a sentiment dictionary in the movie comment field; carrying out emotion calculation on the movie comments by utilizing a designed emotion calculation method to judge emotion polarity; then performing emotion polarity judgment on the comments by utilizing the weak annotation information of the user scores; wherein if the comment emotion polarity obtained through emotion calculation is consistent with the comment emotion polarity judged by the weak annotation information, the emotion polarity of themovie comment can be obtained, and if the comment emotion polarity obtained through emotion calculation is not consistent with the comment emotion polarity judged by the weak annotation information, the emotion polarity of the movie comment is judged according to emotion calculation.

Description

technical field [0001] The invention belongs to the technical field of text emotion analysis in natural language processing, in particular to an emotion analysis method for movie reviews on Douban.com. Background technique [0002] As a common film social media comment platform, Douban.com carries a huge amount of information. After each movie comes out, a large number of netizens will post comments on Douban. These massive subjective comment text data contain rich emotional information. How to analyze the emotional polarity of these emotional information is a very meaningful thing. [0003] In the existing technology, there are mainly two methods for text sentiment analysis, one is based on machine learning, but it needs to select the appropriate feature training model, so as to realize the emotional polarity judgment of the text; the other is to use Based on the method of emotional dictionary, the emotional weight of the text is calculated by designing a reasonable emotio...

AI Technical Summary

Problems solved by technology

[0005] However, the above two methods have shortcomings. First, the method based on machine learning requires a large amount of manual labeling data sets, and is not suitable for processing fine-grained texts such as movie reviews; although the method based on sentiment lexicon is suitable for processing fine-grained texts , but the emotional words included are limited

Images