loading page

Text Classification Method Based on PEGCN
  • Zelin Guo,
  • Ruidong Zhang,
  • Hai Huan
Zelin Guo
Nanjing University of Information Science and Technology
Author Profile
Ruidong Zhang
Nanjing University of Information Science and Technology
Author Profile
Hai Huan
Nanjing University of Information Science and Technology

Corresponding Author:[email protected]

Author Profile

Abstract

The purpose of text classification is to label the text with known labels. In recent years, the method based on graph neural network (GNN) has achieved good results. However, the existing methods based on GNN only regard the text as the set of co-occurring words, without considering the position information of each word in the statement. Meanwhile, this method mainly extracts node features, but neglects the use of edge features between nodes. To solve these problems, a new text classification method, graph convolutional network using positions and edges (PEGCN), is proposed. In the word embedding section, a positional encoding input representation is employed to enable the neural network to learn the relative positional information among words. Meanwhile, the dimension of the adjacency matrix is increased to extract the multi-dimensional edge features. Through experiments on multiple text classification datasets, the proposed method is shown to be superior to the traditional text classification method, and has achieved a maximum improvement of more than 4%.
20 Apr 2023Submitted to Expert Systems
21 Apr 2023Submission Checks Completed
21 Apr 2023Assigned to Editor
04 May 2023Reviewer(s) Assigned
08 Jun 2023Review(s) Completed, Editorial Evaluation Pending
20 Jun 2023Editorial Decision: Revise Minor
23 Jun 20231st Revision Received
26 Jun 2023Submission Checks Completed
26 Jun 2023Assigned to Editor
14 Jul 2023Reviewer(s) Assigned
31 Aug 2023Review(s) Completed, Editorial Evaluation Pending
01 Sep 2023Editorial Decision: Revise Minor
03 Sep 20232nd Revision Received
05 Sep 2023Submission Checks Completed
05 Sep 2023Assigned to Editor
18 Sep 2023Reviewer(s) Assigned
03 Nov 2023Review(s) Completed, Editorial Evaluation Pending
05 Nov 2023Editorial Decision: Accept