A sentiment classification method and system

Abstract

The present invention is applicable to the field of computer technology, and provides a sentiment classification method and system. The method includes: analyzing the text to be classified according to the rhetorical structure theory to obtain a rhetorical structure analysis tree; obtaining the information of each node in the rhetorical structure analysis tree The initial vector, the node includes: input gate, output gate, memory cell, hidden state and forget gate; according to the point product of the output gate of the node and the hyperbolic tangent function value of the memory cell, the hidden state of the node is obtained; according to Hidden state of nodes, sentiment classification by classifier function. The present invention builds the text to be classified into a rhetorical structure analysis tree, in which there are two node fragments in each layer, and each node has its own forgetting gate, during the learning process, children are selected through the forgetting gate Node information, constantly updating cell status, discarding unimportant information, adding core content, improving semantic feature expression, thereby improving classification accuracy.

Description

technical field [0001] The invention belongs to the technical field of computers, and in particular relates to an emotion classification method and system. Background technique [0002] Due to the problem of gradient disappearance in Recurrent Neural Networks (RNN, Recurrent Neural Networks), in recent years, a chain-structured long-short-term memory network (LSTM, Long short-term memory) has been proposed and widely studied. It adds a memory cell structure to the original RNN to store information. This improvement makes LSTM have a strong ability to protect sequence information over time, so it can capture long-term, long-distance dependencies. Solved the gradient vanishing problem of RNN. However, the previous research on LSTM was based on the linear chain structure of time series. Later, after research, the chained LSTM was extended to the tree structure and constructed through the syntax analysis tree structure, which improved the expression of semantic features. These ...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method and system for emotion classification, aiming to solve the problem that the semantic features learned in the prior art are not sufficient and accurate, resulting in poor effect of emotion classification

Images