Next Article in Journal
Investigation of Defect Formation in Monolithic Integrated GaP Islands on Si Nanotip Wafers
Previous Article in Journal
Controller Design for Autonomous Direct Current Microgrid Operation
Previous Article in Special Issue
An Improved Lightweight YOLOv5s-Based Method for Detecting Electric Bicycles in Elevators
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Enhanced Text Classification with Label-Aware Graph Convolutional Networks

1
Department of Information Engineering and Computer Science, Feng Chia University, Taichung 407, Taiwan
2
Department of Information Management, Chaoyang University of Technology, Taichung 413, Taiwan
*
Author to whom correspondence should be addressed.
Electronics 2024, 13(15), 2944; https://doi.org/10.3390/electronics13152944 (registering DOI)
Submission received: 30 June 2024 / Revised: 18 July 2024 / Accepted: 25 July 2024 / Published: 25 July 2024

Abstract

Text classification is an important research field in text mining and natural language processing, gaining momentum with the growth of social networks. Despite the accuracy advancements made by deep learning models, existing graph neural network-based methods often overlook the implicit class information within texts. To address this gap, we propose a graph neural network model named LaGCN to improve classification accuracy. LaGCN utilizes the latent class information in texts, treating it as explicit class labels. It refines the graph convolution process by adding label-aware nodes to capture document–word, word–word, and word–class correlations for text classification. Comparing LaGCN with leading-edge models like HDGCN and BERT, our experiments on Ohsumed, Movie Review, 20 Newsgroups, and R8 datasets demonstrate its superiority. LaGCN outperformed existing methods, showing average accuracy improvements of 19.47%, 10%, 4.67%, and 0.4%, respectively. This advancement underscores the importance of integrating class information into graph neural networks, setting a new benchmark for text classification tasks.
Keywords: text classification; graph convolutional networks; label-aware; word–class correlation; deep learning text classification; graph convolutional networks; label-aware; word–class correlation; deep learning

Share and Cite

MDPI and ACS Style

Lin, M.-Y.; Liu, H.-C.; Hsush, S.-C. Enhanced Text Classification with Label-Aware Graph Convolutional Networks. Electronics 2024, 13, 2944. https://doi.org/10.3390/electronics13152944

AMA Style

Lin M-Y, Liu H-C, Hsush S-C. Enhanced Text Classification with Label-Aware Graph Convolutional Networks. Electronics. 2024; 13(15):2944. https://doi.org/10.3390/electronics13152944

Chicago/Turabian Style

Lin, Ming-Yen, Hsuan-Chun Liu, and Sue-Chen Hsush. 2024. "Enhanced Text Classification with Label-Aware Graph Convolutional Networks" Electronics 13, no. 15: 2944. https://doi.org/10.3390/electronics13152944

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop