PI: Andrew Olney
Co-PIs: Natalie Person, Sidney D'Mello, Art Graesser
We know that students benefit from individualized training, but tutors can vary widely
in ability and experience. How can IIS level the playing field so that automated tutors
are consistently excellent?
Guru, our second-generation animated tutor, stems from AutoTutor, but uses what we’ve
learned about expert tutoring strategies and dialogue for a more effective tutoring
Guru seeks to improve educational outcomes on the Tennessee Gateway Science Test that
high school students must pass to receive a diploma.
We focus on maintaining student motivation, and we are collecting self-report, eyetracking,
and other behavioral measures to make interacting with Guru as enjoyable as possible.
- Guru: A Computer Tutor that Models Expert Human Tutors. Funding Agency: IES. $1,858,176
- D'Mello, S., Olney, A., & Person, N. (2010). Mining collaborative patterns in tutorial
dialogues. Journal of Educational Data Mining, 2(1), 1–37.
- Olney, A. M., Graesser, A. C., & Person, N. K. (2010). Tutorial dialogue in natural
language. In R. Nkambou, R. Mizoguchi & J. Bourdeau (Eds.), Advances in intelligent
tutoring systems (pp. 181–206). Berlin, Germany: Springer-Verlag.
- Graesser, A. C., Conley, M., & Olney, A. M. (2011). Intelligent tutoring systems.
In K. R. Harris, S. Graham, & T. Urdan (Eds.), APA handbook of educational psychology,
Volume 3: Application to learning and teaching. Washington, DC: American Psychological