Improving Intelligent Tutoring Systems
, Worcester Polytechnic Institute
Date: Friday, March 07, 2003
Time: 2:30 PM to 3:30 PM
Relevant URL: http://www.algebratutor.org/
Speaker URL: None
TALK: Improving Intelligent Tutoring Systems
Did you know that 1% of American high school students are using intelligent tutors in their high schools? Some intelligent tutoring systems have been shown to lead to large learning gains for students (e.g., 1 standard deviation effect size). That is more than twice as effective as traditional computer-aided instruction (meta-analyses has shown about .4 standard deviation effect sizes). Nevertheless, current intelligent tutors still have a long way to go before they reach the effectiveness of experienced one-on-one tutors (which Bloom reported led to effect sizes of 2 standard deviations). I will report on some recent investigations meant to improve intelligent tutoring systems. One idea is to study what experienced human tutors do, and try to get the system to respond in a similar way. I will also discuss other work at the forefront of intelligent tutoring systems research including authoring tools, data mining and the application of intelligent tutoring systems to the Massachusetts Comprehensive Assessment Systems (MCAS).
Dr. Neil Heffernan, after graduating from Amherst College, taught mathematics to eighth grade students in Baltimore City as part of Teach for America, a program that selectively recruits top candidates to teach in inner-city schools. Later, Neil attended Carnegie Mellon University's Computer Science department to do research in creating educational software that leads to higher student achievement. For his dissertation, Neil built the first intelligent tutoring system that incorporated a model of tutorial dialog. This system has been shown to lead to higher student learning, by getting students to think more deeply about problems. It is based upon detailed studies of student learning as well as studies of experienced human teachers. The system (free at www.AlgebraTutor.org) is the most widely used web-based intelligent tutoring system. It has been used by thousands of students and teachers and has been awarded many educational awards. Carnegie Mellon has applied for a patent for this unique web-based tutor. Neil is a Spencer Foundation / National Academy of Education Postdoctoral Research Fellow. Neil is now an assistant professor at Worcester Polytechnic Institute.
Created by Linda L. Julien at Wednesday, June 19, 2013 at 6:21 AM.