Technology to Review Online Videos for Education (NSF EAGER)

AI-driven discovery of online educational videos.

Abstract: The popularity of online videos creates challenges for parents and educators of young children. They want children to watch educational videos but lack tools to efficiently distinguish educational from non-educational content within the growing universe of online videos. Our multidisciplinary team of education and machine learning researchers propose a project to develop TROVE: Technology to Review Online Videos for Education. TROVE will be a machine learning-based content classification engine to identify early childhood mathematics content in online videos. Existing systems for classifying educational content in online videos rely primarily on human review. TROVE’s capability will enable new approaches to increase young children’s exposure to developmentally appropriate educational mathematics content in videos, which has been shown to improve later mathematics learning outcomes.

Susmit Jha
Susmit Jha
Technical Director, NuSCI

My research interests include artificial intelligence, formal methods, machine learning and dynamical systems.