PI: Andrew Olney
Intelligent tutoring systems are very effective but require a great deal of AI knowledge engineering, making them expensive to produce.
The BrainTrust project addresses this authoring problem by inverting the tutoring system:
- When a student navigates to an online textbook, the BrainTrust browser generates a virtual student.
- As the human teaches the student, they engage in reading comprehension activities
- Help the student better understand the text
- Create knowledge representations for a future intelligent tutoring system for that text
- Enhanced Authoring with the BrainTrust System. Funding Agency: Office of Naval Research. $211,024.
- EAGER: Using Crowdsourced Virtual Students to Create Intelligent Tutors. Funding Agency:
- Olney, A. M., Brawner, K., Pavlik, P., & Koedinger, K. R. (2015). Emerging Trends in Automated Authoring. Design recommendations for adaptive intelligent tutoring systems: Learner modeling, Vol. 3 of Adapive Tutoring (pp. 227-242). Orlando: U.S. Army Research Laboratory.
- Olney, A. M., & Cade, W. L. (2015). Authoring Intelligent Tutoring Systems Using Human Computation: Designing for Intrinsic Motivation. In D. D. Schmorrow & C. M. Fidopiastis (Eds.), Foundations of Augmented Cognition (Vol. 9183, pp. 628–639). Springer International Publishing.