Enhancing Scientific Reasoning and Explanation Skills with Conversational Agents

This paper investigates the use of conversational agents to scaffold on-line collaborative learning discussions through an approach called Academically Productive Talk (APT). In contrast to past work on dynamic support for collaborative learning, which has involved using agents to elevate the conceptual depth of collaborative discussion by leading students in groups through directed lines of reasoning, this APT based approach lets students follow their own lines of reasoning and promotes productive practices such as deep explaination and refinement of ideas. The study provides evidence that one form of the support, namely the Revoicing support, lead to significantly more learning within an online collaborative learning activity and resulted in higher quality explanations for predictions within that session.