Visualising Argumentation Graphs with Graph Embeddings and t-SNE

TL;DR

This paper explores the use of t-SNE visualisation on argumentation graphs through various graph embedding methods, revealing structural properties and suggesting new research directions.

Contribution

It introduces a novel application of t-SNE to argumentation graphs using multiple embedding techniques, highlighting its potential for structural analysis.

Findings

t-SNE effectively visualises argumentation graph structures

Different embedding methods reveal diverse structural insights

The approach opens new avenues for research in argumentation analysis

Abstract

This paper applies t-SNE, a visualisation technique familiar from Deep Neural Network research to argumentation graphs by applying it to the output of graph embeddings generated using several different methods. It shows that such a visualisation approach can work for argumentation and show interesting structural properties of argumentation graphs, opening up paths for further research in the area.