Leveraging Graph Neural Networks for Text Classification with Semantic and Structural Insights

Remya R. K. Menon, Jyothish S L, Ajith B. T. K.

2025

Abstract

Applications which involve text classification may still need a breakthrough in capturing the latent structure in the text and more complex dependencies which limits its capacity to make correct predictions. This paper presents a new approach to a text classification application in which a hybrid graph representation learning algorithm has been used to demonstrate interactions between latent semantic and structural data in text documents. Text is represented as a graph, where a node represents a sentence and an edge represents the semantic relationship between two nodes. With nodes converted to embeddings generated through Sentence-BERT, it offers contextualized representations for every node. Along with this framework, we also learn low-dimensional representations of the text graphs using graph auto-encoders. Our model thus enhances generalization and has a powerful representation for downstream tasks by minimizing the difference between reconstructed and input graphs. Experimental results demonstrate that our model surpasses traditional methods by successfully integrating semantic and structural information to enhance classification accuracy. This work contributes to the advancement of GNN-based architectures for text retrieval, demonstrating the potential of graphs in natural language processing.

Paper Citation

in Harvard Style

R. K. Menon R., S L J. and B. T. K. A. (2025). Leveraging Graph Neural Networks for Text Classification with Semantic and Structural Insights. In Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT; ISBN 978-989-758-763-4, SciTePress, pages 93-104. DOI: 10.5220/0013587700004664

in Bibtex Style

@conference{incoft25,
author={Remya R. K. Menon and Jyothish S L and Ajith B. T. K.},
title={Leveraging Graph Neural Networks for Text Classification with Semantic and Structural Insights},
booktitle={Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT},
year={2025},
pages={93-104},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013587700004664},
isbn={978-989-758-763-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT
TI - Leveraging Graph Neural Networks for Text Classification with Semantic and Structural Insights
SN - 978-989-758-763-4
AU - R. K. Menon R.
AU - S L J.
AU - B. T. K. A.
PY - 2025
SP - 93
EP - 104
DO - 10.5220/0013587700004664
PB - SciTePress