Sequence Graph Network for Online Debate Analysis

TL;DR

This paper introduces a Sequence Graph Network that models online debates by capturing both sequential and interaction dynamics, leading to improved analysis of complex discussion processes.

Contribution

It proposes a novel sequence-graph approach with a Sequence Graph Attention layer to better model interactions and context in online debates.

Findings

Sequence Graph Networks outperform existing methods in debate analysis

The approach effectively models participant interactions and argument flow

Experimental results demonstrate superior accuracy in online debate tasks

Abstract

Online debates involve a dynamic exchange of ideas over time, where participants need to actively consider their opponents' arguments, respond with counterarguments, reinforce their own points, and introduce more compelling arguments as the discussion unfolds. Modeling such a complex process is not a simple task, as it necessitates the incorporation of both sequential characteristics and the capability to capture interactions effectively. To address this challenge, we employ a sequence-graph approach. Building the conversation as a graph allows us to effectively model interactions between participants through directed edges. Simultaneously, the propagation of information along these edges in a sequential manner enables us to capture a more comprehensive representation of context. We also introduce a Sequence Graph Attention layer to illustrate the proposed information update scheme. The experimental results show that sequence graph networks achieve superior results to existing methods in online debates.