Mehran Sahami : 2012 Plenary Session

 

Tuesday, April 3, 2012
Location: Fisher Conference Center, Arrillaga Alumni Center

"Using Machine Learning to Model How Students Learn to Program"
2:00pm - 2:30pm

Abstract:

Despite the potential wealth of educational indicators expressed in students' approaches to completing programming assignments, how students arrive at their final solution is largely overlooked in courses-only their final program submission is evaluated as an indicator of their understanding of how to solve a particular programming problem. In this talk, we present a methodology which uses machine learning techniques to autonomously create a graphical model of how students in an introductory programming course progress through a homework assignment. We subsequently show that this model is predictive of which students will struggle with material presented later in the class. Our eventual goal is to be able better understand students' learning and the conceptual difficulties they may encounter as novice programmers so as to be able to provide better and more personalized guidance to them during their learning process.


Bio:

Mehran Sahami is an Associate Professor and Associate Chair for Education in the Computer Science department at Stanford University. He is also the Robert and Ruth Halperin University Fellow in Undergraduate Education. Prior to joining the Stanford faculty, he was a Senior Research Scientist at Google for several years. His research interests include computer science education, machine learning, and information retrieval on the Web. He serves as co-chair of Computer Science Curricula 2013, a joint ACM/IEEE-CS effort to set international guidelines for undergraduate programs in computer science for the coming decade. He also recently spearheaded the redesign of Stanford's undergraduate CS curriculum, which within two years led to a near doubling in the number of students pursuing CS as a major.