Syntactic analysis-based microblog sentiment classification method and syntactic analysis-based microblog sentiment classification system

Abstract

A microblog sentiment classification method based on syntactic analysis comprises the steps that S1, microblog short texts used for sentiment analysis are obtained, text category labeling is conducted according to sentiment polarity, and the texts are divided into a training set and a test set; s2, respectively carrying out data preprocessing on the training set and the test set; s3, performing dependency syntax analysis on each preprocessed sample, and constructing a feature word bank in combination with an external emotion feature dictionary; s4, according to a pre-constructed sentiment feature word bank, feature extension is carried out on the initial feature sets of the training set and the test set respectively, and the feature weight of each feature word is calculated by using TFIDF and vectorized to represent the text; and S5, training a Bayesian classifier according to the expanded training sample set, and performing classification operation on the expanded test samples according to the Bayesian classification model to obtain a microblog emotion classification result. The invention further comprises a microblog sentiment classification system based on syntactic analysis.

Description

technical field [0001] The invention relates to the technical field of Chinese short text classification, in particular to a method and system for classifying microblog emotions based on syntactic analysis. Background technique [0002] As one of the most popular social software in the contemporary era, Weibo has a user base of over 100 million since its development. Due to the rapid release of Weibo information and its wide spread, it has become the most popular social networking platform among the public. On Weibo, everyone can speak freely, express some life dynamics and views on current affairs news, entertainment gossip, and at the same time, we can quickly obtain the information we want to know. While the efficiency and real-time nature of Weibo communication brings us convenience, it will also bring some negative impacts to society. [0003] Sentiment analysis of short texts on Weibo focuses on judging the positive and negative emotional tendencies of Weibo through s...

AI Technical Summary

Problems solved by technology

The present invention effectively uses the syntactic dependency relationship to extract the emotional features of short microblog texts, and then expands the features with the help of an external emotional lexicon, effectively solving the defect of poor classification effect caused by the sparse emotional features of short microblog texts

Images