Simulating Smooth Tutorial Dialogue with Pedagogical Value

This paper describes the design of AutoTutor, a fully automated computer tutor that simulates dialogue moves of normal human tutors and that will eventually incorporate sophisticated tutoring strategies. AutoTutor follows a curriculum script that presents subtopics in di erent forms, such as didactic content, graphic displays, questions, and problems. The tutor selects dialogue moves that assist the learner in the active construction of knowledge as the learner answers questions or solves problems posed by the tutor. The goal is to have the tutor produce dialogue moves that t the conversational context, that are sensitive to the learner's abilities, and that have pedagogical value. The dialogue moves include immediate feedback, pumping, prompting, splicing, hinting, requestioning, and summarizing. The tutor's moves are delivered by a talking head with appropriate facial expressions and synthesized speech. The rst version of AutoTutor should be completed in the spring of 1998 on the topic of computer literacy. Can a Computer be a Good Partner in