Emotional tendency prediction method, device and system and storage medium

Abstract

The invention discloses a graph neural network (GNN)-based emotional tendency prediction method, device and system, and a computer storage medium. The graph neural network-based emotional tendency prediction method comprises the steps of firstly, obtaining a segment of text information; then, converting the text information into the graphic structure data taking the words as the nodes and taking the similarity among the words as edges; converting the graphic structure data into an adjacent matrix formed by the similarity between words; and then performing emotional tendency prediction on the adjacent matrix through an emotional classification model. According to the emotion tendency prediction method, when a long text is processed, the text information is converted into the graphic structure data through the similarity between words, so that on one hand, the advantages of a graphic neural network can be utilized to contain the semantics as many as possible, and on the other hand, by aggregating the similar words together, the emotional tendency characteristics with the most representative significance can be extracted more easily, and the prediction result is more accurate.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence (AI), in particular to a method, device, system and computer storage medium for predicting emotional tendencies based on a graph neural network (GNN). Background technique [0002] Sentiment classification is a common task in natural language processing. Specifically, a piece of text information is given, and the sentiment classification model is used to predict the emotional tendency of the text information. [0003] At present, most of the emotional tendency prediction methods are based on word vector sequences and convolutional neural networks. This emotional tendency prediction method mainly uses the following method when converting sentences in text information in the early stage: first, segment the sentences, and convert the extracted words into word vectors; then, convert the word vectors according to the The positions in are arranged in order to form a sentence ma...

AI Technical Summary

Problems solved by technology

This will lead to the following problems: 1) When the size of the sentence matrix exceeds the matrix size that the neural network can handle, only part of the word vector can be discarded, and part of the matrix can be intercepted for processing

This is equivalent to the fact that when predicting the emotional tendency, only the first paragraph, interruption or rear paragraph of a sentence is used, and the possibility of semantic loss is extremely high at this time; 2) Even if the size of the sentence matrix does not exceed the matrix that the neural network can handle Size, because words related to emotional orientation may be scattered in various positions of the matrix, the size of a single convolution window can also limit the accuracy of emotional orientation feature extraction

Images