Detecting Attackable Sentences in Arguments

TL;DR

This paper analyzes what makes sentences in online arguments attackable, identifying key features and demonstrating that machine learning can effectively detect attackable sentences, aiding argument refutation.

Contribution

It provides the first large-scale analysis of sentence attackability and develops models that outperform baselines in automatic detection.

Findings

Attackability correlates with sentence content, proposition types, and tone.

External knowledge sources improve attackability detection.

Machine learning models perform well, comparable to laypeople.

Abstract

Finding attackable sentences in an argument is the first step toward successful refutation in argumentation. We present a first large-scale analysis of sentence attackability in online arguments. We analyze driving reasons for attacks in argumentation and identify relevant characteristics of sentences. We demonstrate that a sentence's attackability is associated with many of these characteristics regarding the sentence's content, proposition types, and tone, and that an external knowledge source can provide useful information about attackability. Building on these findings, we demonstrate that machine learning models can automatically detect attackable sentences in arguments, significantly better than several baselines and comparably well to laypeople.