Text emotion classification method and device, computer device and storage medium

Abstract

The invention discloses a text emotion classification method and device, a computer device and a storage medium. The method comprises: acquiring a word vector corresponding to a text to be subjected to emotion recognition, inputting the word vector into a trained convolutional neural network model, and a text vector output by a full connection layer of the trained convolutional neural network model is acquired to serve as a text recognition vector; carrying out linear discriminant analysis and dimension reduction on the text recognition vector to obtain a text vector after dimension reduction;and taking the text vector after dimensionality reduction as the input of a text emotion classifier for classification to obtain a text emotion recognition result. According to the method, more effective features are extracted from the emotion recognition text to be subjected to emotion recognition through the convolutional neural network and are input into a traditional classifier, and the classification accuracy is improved.

Description

technical field [0001] The present invention relates to the technical field of text emotion recognition, in particular to a text emotion classification method, device, computer equipment and storage medium. Background technique [0002] At present, traditional classification models (naive Bayesian, SVM) or deep neural networks (CNN, LSTM) are generally used in text classification problems, but traditional classification models are difficult to capture deeper features, and deep learning models are multi-classified at the end. The classifiers used in the layer are weak and it is difficult to take advantage of traditional classification models. Contents of the invention [0003] The embodiment of the present invention provides a text emotion classification method, device, computer equipment and storage medium, aiming to solve the problem that the classifier used in the last multi-classification layer of the deep learning model in the prior art is weak and cannot be used in th...

AI Technical Summary

Problems solved by technology

[0003] The embodiment of the present invention provides a text emotion classification method, device, computer equipment and storage medium, aiming to solve the problem that the classifier used in the last multi-classification layer of the deep learning model in the prior art is weak and cannot be used in the deep learning model Problems Combining the Strengths of Traditional Classification Models

Images