Impact of Argument Type and Concerns in Argumentation with a Chatbot

TL;DR

This paper explores how argument type and concerns influence chatbot argumentation, presenting methods to acquire relevant arguments and meta-information to enhance persuasion in dialogue systems.

Contribution

It introduces novel methods for acquiring arguments, counterarguments, and meta-level data to improve chatbot persuasion capabilities.

Findings

Methods effectively acquire relevant arguments and counterarguments.

Using meta-level information improves chatbot persuasion success.

Participants found the chatbot more convincing with the new methods.

Abstract

Conversational agents, also known as chatbots, are versatile tools that have the potential of being used in dialogical argumentation. They could possibly be deployed in tasks such as persuasion for behaviour change (e.g. persuading people to eat more fruit, to take regular exercise, etc.) However, to achieve this, there is a need to develop methods for acquiring appropriate arguments and counterargument that reflect both sides of the discussion. For instance, to persuade someone to do regular exercise, the chatbot needs to know counterarguments that the user might have for not doing exercise. To address this need, we present methods for acquiring arguments and counterarguments, and importantly, meta-level information that can be useful for deciding when arguments can be used during an argumentation dialogue. We evaluate these methods in studies with participants and show how harnessing these methods in a chatbot can make it more persuasive.