Using Conceptual Models to Implement Natural Language Pedagogic Agent-Student Conversations
The last several decades have seen a growing trend in incorporating pedagogic conversational agents in interactive learning environments. Software systems have increasingly integrated intelligent virtual agents that can interact with students in natural language to fulfill specific tasks such as reviewing content or providing tutor training. The use of an agent-based approach in education has shown many benefits. However, certain design and development issues are still unresolved. This article focuses on the potentials of employing conceptual models to generate agent-student dialog and introduces a new mixed-initiative general domain agent called JARO. The authors report on the procedure for creating the initial conceptual model and discuss its use in guiding agent-student conversations adapted to students' individual learning needs. The stages of implementation of the model as well as the model's viability tested in a proof-of-concept experiment are addressed.