Faculty Advisor

Heffernan, Neil

Abstract

The ASSISTment online tutoring system was used by over 600 students during the school year 2004-2005 and MCAS test results were obtained for those students. Students completed online items marked with skills from our four skill models. Using Bayesian networks to predict the MCAS test scores, we found that the finer-grained of the skill models allowed for more accurate prediction. Other topology approaches such as skill hierarchy are explored as well as the effect of parameter learning on prediction performance. The work from this paper has been peer reviewed and accepted for publication at the 8th annual International Conference on Intelligent Tutoring Systems, Taiwan.

Publisher

Worcester Polytechnic Institute

Date Accepted

January 2006

Major

Computer Science

Project Type

Major Qualifying Project

Accessibility

Restricted-WPI community only

Advisor Department

Computer Science

Advisor Program

Computer Science

Share

COinS