ARGUS: Seeing the Influence of Narrative Features on Persuasion in Argumentative Texts

2026-02-27

AI Summary

This study investigates how narrative elements influence the persuasiveness of unstructured online arguments and identifies key narrative features associated with persuasive success. To this end, we propose ARGUS, a novel framework that systematically integrates narrative theory with computational models of persuasion. We construct and annotate a large-scale corpus from ChangeMyView, comprising argumentative posts enriched with story annotations and six distinct narrative dimensions. Leveraging encoder-based classifiers and zero-shot large language models, we enable automatic identification and quantitative analysis of narrative components. Our findings demonstrate that specific narrative dimensions—particularly emotional arousal and character development—significantly enhance persuasive outcomes. This work establishes a new paradigm at the intersection of computational argumentation and narrative analysis, offering both methodological tools and empirical evidence for future research.

Technology Category

• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Knowledge Representation and Reasoning: Argumentation
• Multiagent Systems: Agreement, Argumentation & Negotiation

Application Category

• Web Mining and Content Analysis: Bridging structured and unstructured data
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Social Networks and Social Media: Computational social science

Abstract

Can narratives make arguments more persuasive? And to this end, which narrative features matter most? Although stories are often seen as powerful tools for persuasion, their specific role in online, unstructured argumentation remains underexplored. To address this gap, we present ARGUS, a framework for studying the impact of narration on persuasion in argumentative discourse. ARGUS introduces a new ChangeMyView corpus annotated for story presence and six key narrative features, integrating insights from two established theoretical frameworks that capture both textual narrative features and their effects on recipients. Leveraging both encoder-based classifiers and zero-shot large language models (LLMs), ARGUS identifies stories and narrative features and applies them at scale to examine how different narrative dimensions influence persuasion success in online argumentation.

Problem

• narrative features
• persuasion
• argumentative texts
• story presence
• online argumentation

Innovation

• narrative features
• persuasion
• argumentative discourse
• large language models
• corpus annotation