Short text sentiment analysis method based on CNN bidirectional GRU attention mechanism

Abstract

The invention discloses a short text sentiment analysis method based on a CNN (Convolutional Neural Network) bidirectional GRU attention mechanism. The method comprises the following steps: preprocessing a short text, denoising, segmenting words, labeling part of voice, and removing stop words; expressing sentences into a word sequence through negative sampling training by taking words as units through a continuous bag-of-words model (CBOW), and mapping the word sequence into a multi-dimensional vector to construct a word vector set; calculating the occurrence frequency of sentiment words in different data set documents, calculating sentiment scores, and converting the sentiment scores into a sentiment feature vector matrix; word embedding and feature embedding topology serves as input ofa convolutional neural network, and sentence representation is obtained through convolution and pooling; through a bidirectional GRU recurrent neural network, negative word turning words are set as parameter query items of an attention mechanism to obtain representation; and combining the two representation topologies to serve as full connection layer input, and outputting an emotion analysis result.

Description

technical field [0001] The invention belongs to the field of natural language processing, in particular to a short text sentiment analysis method based on CNN bidirectional GRU attention mechanism Background technique [0002] With the rapid development of the Internet, more and more users express their opinions and express their emotional comments through social media, most of which exist in the form of short texts. Hot events will arouse widespread concern and discussion in the society. It is an extremely challenging task to grasp the direction of public opinion in a timely manner and obtain user emotional tendencies. [0003] Sentiment analysis can understand the public's emotional changes on hot events by preprocessing, analyzing, and mining users' emotional tendencies. It is also one of the important directions of natural language processing. Sentiment analysis research methods are mainly divided into dictionary-based methods, machine learning-based methods, and deep l...

AI Technical Summary

Problems solved by technology

The method based on machine learning relies on selecting effective feature combinations and using classifiers for sentiment classification, but this method requires a large number of manually labeled data sets to train the model, which is time-consuming and laborious

The method based on deep learning can mine deep semantic and emotional meanings and is widely used. However, supervised deep learning still requires a large number of annotations, while unsupervised methods have higher requirements for the semantic association of text, among which negative words, degree adverbs, transition words The use of etc. may cause the emotional polarity shift of the sentence to affect the accuracy of the sentiment analysis results, and further development and improvement are needed

Images