CSAIL Event Calendar

Towards Automatically Detecting the Robustness of Student Learning

Recent theory and research has emphasized the importance of
promoting robust learning that prepares students for future learning.
The behavior of intelligent tutoring systems is driven to large
degrees by sophisticated automated assessments of student learning.
However, these assessments typically do not consider how robust
student learning is. In this talk, I will present automated detectors
which explicitly detect whether a student has acquired learning which
will transfer to better performance on related skills and prepare the
student for future learning. This work is conducted in the context of
an intelligent tutoring system for college genetics. I compare these
detectors to a classic method for assessing student knowledge,
Bayesian Knowledge-Tracing, to assess how effective the detectors are
at assessing robust learning. I also analyze how much information the
detectors need in order to make accurate assessments, towards using
the detectors to deliver timely interventions.

BIO:
Ryan Shaun Joazeiro de Baker is the Julius and Rosa Sachs
Distinguished Lecturer at Columbia University Teachers College, in
2012-2013. He earned his Ph.D. in Human-Computer Interaction from
Carnegie Mellon University, and was a post-doctoral fellow in the
Learning Sciences at the University of Nottingham. He earned his
Bachelor's Degree (Sc.B.) in Computer Science from Brown University.
Dr. Baker has been Assistant Professor of Psychology and the Learning
Sciences at Worcester Polytechnic Institute. He previously served as
the first Technical Director of the Pittsburgh Science of Learning
Center DataShop, the largest public repository for data on the
interaction between learners and educational software. He is currently
serving as the founding President of the International Educational
Data Mining Society, and as Associate Editor of the Journal of
Educational Data Mining.

See other events happening in August 2012