A Text Classification Model of Graph Convolutional Neural Network Based on Attention Mechanism

The graph convolutional neural network can effectively extract graph data features, and fully consider the association relationship between samples. However, the traditional graph convolutional neural network text classification model in which document vertices aggregate information on surrounding vocabulary vertices is to update document vertices when updating information using the vocabulary vertices connected to them, and this approach does not fully consider the similarities and differences of document vertices for each vocabulary connected to them, while in fact, each vocabulary is not of the same importance to the document. Although this paper proposes a lightweight graph attention mechanism to avoid the problem of excessive computational resource consumption, and builds a graph convolutional text classification model based on the attention mechanism to guide the model to focus on more relevant words and extract features from the perspective of feature diversity to improve the performance of text classification.