Convolution-neural-network-based text emotion classification method

Abstract

The invention relates to a convolution-neural-network-based text emotion classification method. The method comprises: a text linguistic data set is collected and data in a text are expressed into one sentence; pretreatment is carried out on the collected text linguistic data set and emotion text linguistic data are classified into training set linguistic data and testing set linguistic data; training is carried out on the text linguistic data set after pretreatment by using a word2vec tool to obtain a word vector model and a text vector is also obtained; the text vector of the training set linguistic data is inputted into a convolution neural network and training is carried out to obtain an emotion classification model; and the text vector of the testing set linguistic data is inputted into the convolution neural network, emotion type classification is carried out on the trained emotion classification model, and an accurate rate of emotion classification is calculated. Therefore, a problem that lots of artificial marks are needed during the previous classification process can be solved.

Description

technical field [0001] The invention relates to the technical field of text classification, in particular to a text sentiment classification method based on a convolutional neural network. Background technique [0002] The era of the 21st century is the era of information. With the rapid development and improvement of computer technology and data storage technology, the application field has also been rapidly expanded, and the world is undergoing earth-shaking changes with the influx of information. Text data Resources are also growing rapidly. For many users and enterprises, facing such a large amount of text information, it becomes extremely difficult to obtain meaningful, relevant and targeted information. So classifying text information is a very valuable problem. [0003] Sentiment analysis is an important branch of natural language processing, especially in the classification method aimed at extracting the emotional content of the text, there have been many useful pr...

AI Technical Summary

Problems solved by technology

[0004] Most of the existing research methods use shallow learning methods such as support vector machines, maximum entropy, and random walks, but these methods cannot capture many language phenomenon characteristics related to sentiment analysis, and require a lot of manual labeling and training

Images