Computational Argumentation-based Chatbots: a Survey
Federico Castagna, Nadin Kokciyan, Isabel Sassoon, Simon Parsons, Elizabeth Sklar
TL;DR
This survey addresses the gap between conversational chatbots and computational argumentation by systematically classifying and evaluating how argumentation concepts are integrated into chatbots. It covers core elements such as argument mining, argument schemes, reasoning engines, and dialogue protocols, and analyzes how these components are used for extraction, structuring, reasoning, and delivery of replies. The authors synthesize findings from diverse applications, highlight the scarcity of open-domain generative-argumentation bots, and argue that integrating argumentation with modern Transformer-based LLMs could improve explainability, reliability, and user trust. The work suggests a promising research trajectory toward more transparent, persuasive, and reasoning-enabled conversational agents with potential impact across healthcare, education, and beyond.
Abstract
Chatbots are conversational software applications designed to interact dialectically with users for a plethora of different purposes. Surprisingly, these colloquial agents have only recently been coupled with computational models of arguments (i.e. computational argumentation), whose aim is to formalise, in a machine-readable format, the ordinary exchange of information that characterises human communications. Chatbots may employ argumentation with different degrees and in a variety of manners. The present survey sifts through the literature to review papers concerning this kind of argumentation-based bot, drawing conclusions about the benefits and drawbacks that this approach entails in comparison with standard chatbots, while also envisaging possible future development and integration with the Transformer-based architecture and state-of-the-art Large Language models.