AutoTutor is an intelligent tutoring system that helps students learn by holding a conversation in natural language.  AutoTutor appears as an animated agent that acts as a dialog partner with the learner. The animated agent delivers AutoTutor's dialog moves with synthesized speech, intonation, facial expressions, and gestures. Students are encouraged to articulate lengthy answers that exhibit deep reasoning, rather than to recite small bits of shallow knowledge. It may take 50-100 turns between the student and computer tutor for the collaboration to converge on a good answer.  For some topics, there are graphical displays, animations, and interactive simulation.  One version of AutoTutor is sensitive to learner emotions by tracking facial expressions, speech parameters, body posture, and the dialogue history.   Over 15 experiments have been conducted with AutoTutor to help students learn Newtonian physics, computer literacy, and scientific reasoning.  AutoTutor improves learning by nearly one letter grade compared with reading a textbook for an equivalent amount of time. Funding for AutoTutor has come from National Science Foundation, Institute of Education Sciences, and the Department of Defense.

 

 

 

 

You can view our past and current National Science Foundation Grant Proposals to gain a more comprehensive overview of the Autoutor project:

What is AutotTutor? | Contributing Institutions | Use AutoTutor | Publications | People