What Should the Tutor Do When the Student Cannot Answer a Question

Abstract

In this paper we describe how to simulate the behavior of a human tutor when the student cannot answer a question in a dialogue-based tutoring system. This paper describes an implementation of our analysis of human tutoring behavior using the simple plan-based framework of our tutoring system CIRCSIM-Tutor v. 2. By carefully choosing the retry strategies according to our categorization of the student's answer, our machine tutor can simulate some sophisticated human tutoring behaviors, such as hinting and "grain of truth" responses. Introduction We are building an intelligent tutoring system called CIRCSIM-Tutor (CST) designed to help medical students understand the negative feedback system that controls blood pressure and learn to solve problems in physiology. The system presents the student with a description of a physiological change and asks for predictions about the effect of that change on seven important physiological parameters. Then it conducts a dialogue with the student to ...