CS547 Human-Computer Interaction Seminar   (Seminar on People, Computers, and Design)

Fridays 11:30am-12:30pm PT · Gates B3 · Open to the public
Previous | Next
Ken Koedinger
CMU
Using big data to discover tacit knowledge and improve learning
March 7, 2014

Despite our strong sense of conscious awareness of what we know and learn, most of what we know and learn is outside our conscious awareness. One estimate is that the knowledge we are aware of represents only about 30% of what we know. As a consequence, the typical approach of designing educational materials and technologies based on intuition and introspection is limited, even error-prone. Instead, educational design is better based on accurate cognitive models of student knowledge and learning. And accurate cognitive models are best built by combining constraints from computational modeling and from statistical models of student performance data. Online educational technology use is a great source of such data. I will illustrate these points with projects that employ 1) educational data mining and computational modeling to discover better cognitive models and 2) "close the loop" experiments to demonstrate that redesigning personalized online instruction based on these models improves student learning.


Dr. Kenneth Koedinger is Professor of Human-Computer Interaction and Psychology at Carnegie Mellon. His research has contributed new principles and techniques for the design of educational software and has produced basic cognitive science research results on the nature of student thinking and learning. Dr. Koedinger is a co-founder of Carnegie Learning (carnegielearning.com ) and the CMU Director of LearnLab (learnlab.org ). LearnLab is supporting Big Data investigations in education and, more generally, leverages cognitive and computational approaches to support researchers in investigating the instructional conditions that cause robust student learning. See pact.cs.cmu.edu/koedinger.html for more information.