Why/AutoTutor: A Test of Learning Gains from a Physics Tutor with Natural Language Dialog
AC Graesser, GT Jackson, Eric Mathews, HH Mitchell, Andrew McGregor Olney, Ventura, M., Patrick Chipman, Donald R. Franceschetti, Xinyu Hu, Max M. Louwerse, NK Person, Tutoring Research Group · Research portal (Tilburg University) · 2003
Why/AutoTutor is a tutoring system that helps students construct answers to qualitative physics problems by holding a conversation in natural language.Why/AutoTutor provides feedback to the student on what the student types in (positive, neutral, negative feedback), pumps the student for more information, prompts the student to fill in missing words, gives hints, fills in missing information with assertions, identifies and corrects bad answers and misconceptions, answers students' questions, and summarizes answers.In essence, constructivist learning is implemented in a mixedinitiative dialog.Why/AutoTutor delivers its dialog moves with an animated conversational agent whereas students type in their answers via keyboard.We conducted an experiment that compared Why/AutoTutor with two control conditions (Read textbook, nothing) in assessments of learning gains.The tutoring system performed significantly better than the two control conditions on a test similar to the Force Concept Inventory.