A Chinese comment emotion analysis method based on a GRU neural network

Abstract

The invention discloses a Chinese comment emotion analysis method based on a GRU neural network, belonging to the field of natural language processing and deep learning. The method comprises the following steps: (1) firstly loading corpus data and segmenting words by a jieba word segmentation tool; (2) removing some useless pause words and dividing the corpus into a training set and a test set proportionally; (3) using word 2vec to train the word vector of the corpus, taking the mean value of all the word vectors of each sentence to generate the vector of the corresponding sentence, and then using word 2vec model network to carry on the back propagation training to calculate and generate the corresponding word vector finally; (4) inputting the word vector with sentence emotion generated byword 2vec into GRU neural network model for training; (5) constructing the test set according to the training set method, and inputting the GRU neural network to classify the emotion. The method utilizes a classification model based on the GRU neural network to classify emotions, and the speed of the model is remarkably improved at the same time of obtaining a good effect.

Description

technical field [0001] The invention relates to a Chinese comment sentiment analysis method based on a GRU (recurrent unit) neural network, which belongs to the field of natural language processing and deep learning. Background technique [0002] Sentiment classification technology refers to the identification and classification of emotional information expressed by users in comment texts, and generally divides them into positive and negative categories. The emotions of praise and affirmation are divided into positive categories, and the emotions of criticism and negation are divided into negative categories. There are two main methods of sentiment classification technology: the first is the unsupervised classification method using sentiment lexicon, and the second is the supervised classification method based on machine learning. Because sentiment classification based on machine learning methods can achieve better classification results, it has become a mainstream method. ...

AI Technical Summary

Problems solved by technology

Most of the methods can accurately identify sentences expressing accurate emotions, but they cannot accurately identify some comments with irony (excessive praise for the purpose of criticism)

Because this type of method can only classify different word features and cannot extract the hidden emotional expression in the sentence

Images