EquiTutor: Adaptive Learning at Scale
A large-scale study of multimodal tutoring interfaces deployed across three partner school districts.
Overview
EquiTutor deployed an adaptive multimodal tutoring interface across three partner school districts, testing whether real-time cognitive-load estimation could drive modality selection (text vs. audio vs. visual explanation) without increasing extraneous load.
Approach
Three classroom studies, totaling 240 students, measured cognitive load via dual-task response times and compared adaptive modality selection against fixed-modality baselines on learning-gain assessments.
Team & collaborators
Led with Riya Patel, in partnership with three school districts’ instructional technology teams.
Status
Completed in 2024. Results — adaptive modality selection reduced extraneous load without sacrificing learning gains — were published in the International Journal of Artificial Intelligence in Education, and the interaction patterns developed here now inform the AI for Education focus area more broadly.
Back to all research
Abhiraj Bibhar
Department of Sociology and Anthropology
SRM University - Andhra Pradesh