Skip to main content

Distinguished lecture: Zachary Pardos, UC Berkeley

Save to calendar

Sep 13

Date and time: 13 September 2023, 13:00-14:00 CEST (UTC +2)
Speaker: Zachary Pardos, UC Berkeley
Title: Introducing an Open-source Adaptive Tutoring System to Accelerate Learning Sciences Experimentation

Where: Digital Futures hub, Osquars Backe 5, floor 2 at KTH main campus OR Zoom
Meeting ID: 695 6088 7455

Moderator: Olga Viberg,
Administrator: Emil Björnson,

Abstract: Despite the decades-long establishment of effective tutoring principles, no adaptive tutoring system has been developed and open-sourced to the research community. The absence of such a system inhibits researchers from replicating adaptive learning studies, experimenting with new AI capabilities, and exploring various tutoring system design directions. For this reason, adaptive learning research is primarily conducted on a small number of proprietary platforms. In the work described in this talk, recently published at the Conference on Human Factors in Computing Systems, we aim to democratize adaptive learning research with the introduction of the first open-source adaptive tutoring system based on Intelligent Tutoring System principles.

The system, we call Open Adaptive Tutor (OATutor), and its adaptive textbook library, have been iteratively developed over three years with field trials in seven college math classrooms, drawing feedback and design implications from students, educators, and researchers. I will describe how the system can be used as a foundation for exploring large language model integrations and share nascent results from our first evaluation comparing the learning efficacy of ChatGPT to human tutor-generated hints. Connections to course recommender systems research from our lab will be presented with a discussion of future opportunities for community experimentation.

Bio: 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 within higher education systems has been published in venues such as SIGCHI, AAAI, The Internet and Higher Education, and Science. This work has included the development of high-quality tools used by tens of thousands of users, including course recommender systems (, a Python library for Knowledge Tracing (, and an open-source adaptive tutoring system and creative commons content library (

He earned his PhD in Computer Science at Worcester Polytechnic Institute. Funded by a National Science Foundation Fellowship (GK-12), he spent extensive time with K-12 educators and students working to integrate educational technology into the curriculum as a formative assessment tool. After completing his PhD in 2012, he spent one year as a Postdoctoral Associate at the Massachusetts Institute of Technology. At Cal, 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.

Zachary Pardos is a Digital Futures Scholar-in-Residence during August-September 2023.