Text sentiment classification method based on hybrid model

Abstract

A text sentiment classification method based on a hybrid model belongs to the field of computer software. The method mainly comprises a data processing layer, a machine learning processing layer, a CNN processing layer, an LSTM-Attention processing layer and an adaptive decision layer. To-be-classified data is respectively processed by the machine learning processing layer, the CNN processing layer and the LSTM-Attention processing layer; and finally, the processing results are input into an adaptive decision-making layer together, and the adaptive decision-making layer adaptively adjusts theweight of each layer of result according to previous classification results of different processing layers, so that a final classification result is obtained. Compared with a single machine learning method and a single deep learning method, the method has the advantages that the processing effect is obvious, the result has good interpretability, and the application prospect is wide.

Description

technical field [0001] The invention designs a text emotion classification method based on a convolutional neural network, a cyclic neural network and an attention mechanism, and belongs to the field of computer software. Background technique [0002] In today's social network environment, netizens can express their personal opinions on a hot event and express their emotional tendencies through news threads, microblogs, post bars, forums and other forms. If sentiment analysis technology is used to obtain netizens' emotional tendencies from massive online comment texts, it will be of great practical significance whether it is to effectively monitor public opinion for government departments or to extract valuable information from it for other related groups. Therefore, this kind of natural language processing problem has attracted widespread attention of researchers. [0003] Currently commonly used text sentiment classification methods include dictionary-based sentiment clas...

AI Technical Summary

Problems solved by technology

The first two classification methods have high requirements for artificial prior knowledge, and need to manually extract features and construct emotional dictionaries. The processing effect is ideal, but the process is cumbersome

The latter feature is automatically extracted by deep learning, and the processing process is simple, but the result is not interpretable and the effect is worse

Images