Abstract¶
In this presentation, we will cover two open source adaptive tutoring projects, Open Adaptive Tutor (OATutor) and PromptHive, both developed at the UC Berkeley School of Education’s CAHL research lab and released under an MIT or BSD open source license. The former is the first open source adaptive (mastery learning) tutoring system based on ITS principles, that also hosts a creative commons licensed library of content in college intro STEM subjects. The latter is a collaborative authoring tool for subject matter experts that utilizes GenAI to empower them instead of replace them. Both systems have been used to advance educational practice at Cal and at the other two segments of California post-secondary via grants from UC Berkeley EVCP and the California Learning Lab via their AI-FAST program.
Ioannis Anastasopoulos | UC Berkeley¶
Ioannis Anastasopoulos is doctoral student in Learning Sciences and Human Development at the UC Berkeley School of Education. His research interests lie in digital learning environments, specifically adaptive tutors and open educational resources (OERs). He has led the content team of OATutor since its initial pilot development and has worked on constructing a unique and sustainable content environment.
Zachary Pardos¶
Dr. Zachary Pardos is an Associate Professor of Education at UC Berkeley studying adaptive learning and AI. His early scholarship focused on formative assessment using Knowledge Tracing, the predominant model used for estimating skill mastery in computer tutoring system contexts. His recent work designing Human-AI collaborations to pave pathways to and between systems of higher education has been published in venues such as Computers & Education, NeurIPS, The Internet and Higher Education, and Science. This work has included the development of high-quality AI-assistive tools used by tens of thousands of students, administrators, and faculty to support advising, course selection, and STEM subject learning at community colleges and universities. Dr. Pardos earned his PhD in Computer Science from Worcester Polytechnic Institute, followed by a post-doc at the Massachusetts Institute of Technology. At UC Berkeley, he directs the Computational Approaches to Human Learning research lab, teaches in the data science undergraduate program, and is an affiliated faculty in Cognitive Science.