Text classification using graph convolutional network
Graph Convolutional Networks (GCNs) have emerged as a powerful framework for processing and analysing data represented as graphs, finding applications across various domains such as social networks, biological networks, and recommendation systems. This report provides a literature review specificall...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/177159 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | Graph Convolutional Networks (GCNs) have emerged as a powerful framework for processing and analysing data represented as graphs, finding applications across various domains such as social networks, biological networks, and recommendation systems. This report provides a literature review specifically focused on TextGCN, delving into its architecture, applications, and comparative efficacy against other state-of-the-art methods. The effectiveness of TextGCN is assessed through experimentation on IMDb and DBpedia datasets, evaluating its performance across varied data contexts. Additionally, this study explores the utilisation of different activation functions and optimisers, changing the number of hidden layers to enhance the model's capabilities. |
|---|