Ryan Baker on Modeling Student Learning, Moment-by-Moment @ CREATE Lab

03/01/2013 11:00 am – 03/01/2013 12:30 pm Modeling Student Learning, Moment-by-Moment Ryan S.J.d. Baker Julius and Rosa Sachs Distinguished Lecturer Columbia University Teachers College In recent years, intelligent tutoring systems (ITS) have become an increasingly common part of American mathematics and science education. One feature that has supported this development is the student models within intelligent tutors, which have become increasingly accurate at detecting whether a student knows a skill at a given time. From a science of learning perspective, it can be equally important to know when and within which contexts learning occurs. In this talk, I present a machine-learned model that assesses the probability that a student learned a skill at a specific learning opportunity. This model can be used to analyze which skills are learned through insight and “eureka” moments, and which skills are learned more gradually. I also discuss how the pattern of learning over time can be used to predict not just which students learn, and when they learn, but how robust a student’s learning will be. Ryan Shaun Joazeiro de Baker is the Julius and Rosa Sachs Distinguished Lecturer at Columbia University Teachers College for 2012-2013. He earned his Ph.D. in Human-Computer Interaction from Carnegie Mellon University. Baker was previously Assistant Professor of Psychology and the Learning Sciences at Worcester Polytechnic Institute, and 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. His research combines educational data mining and quantitative field observation methods in order to better understand how students respond to educational software, and how these responses impact their learning. He studies these issues within intelligent tutors, simulations, and educational games. In recent years, he and his colleagues have developed automated detectors that make inferences in real-time about students’ engagement, meta-cognition, affect, and robust learning.