Microblog comment viewpoint object classification method based on event graph convolutional neural network

Abstract

The invention relates to a microblog comment viewpoint object classification method based on an event graph convolutional neural network, and belongs to the technical field of natural language processing. The method comprises the following steps: taking a microblog text and comments as document nodes, explicitly taking a keyword co-occurrence relationship, a reply relationship and document similarity as weights of edges of the document nodes, and constructing an adjacent matrix of a graph convolutional neural network on the basis of the weights; giving more weights to the initial features of the document nodes and the word nodes closely related to the keywords; and finally, under the supervision of a small number of labels, learning expressions of word nodes and document nodes so as to finish classification. Experimental results on two event microblog data sets show that compared with other reference models, EventGCN can significantly improve the classification performance of viewpoint objects.

Description

technical field [0001] The invention relates to a method for classifying microblog comment viewpoint objects based on an event graph convolutional neural network, and belongs to the technical field of natural language processing. Background technique [0002] Microblog comment opinion object classification is to divide microblog comments into different categories according to the comment objects, which belongs to the text classification task. Traditional text classification research mainly focuses on feature engineering and classification algorithms. The most commonly used classification features are one-hot, n-gram, IF-IDF, and classification algorithms include Naive Bayes, k-nearest neighbor classifiers and support vector machines. In recent years, neural network models have received extensive attention, and models based on recurrent neural networks (RNN) and convolutional neural networks (CNN) have achieved good results in text classification. Neural network-based model...

AI Technical Summary

Problems solved by technology

These graph neural network-based methods are not specifically designed for microblog opinion object classification, and their performance is limited when applied to this task.

Images