Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Improving Contextual Models of Guessing and Slipping with a Truncated Training Set

Summary: Improving Contextual Models of Guessing and Slipping
with a Truncated Training Set
Ryan S.J.d. Baker, Albert T. Corbett, Vincent Aleven
{rsbaker, corbett, aleven}@cmu.edu
Human Computer Interaction Institute, Carnegie Mellon University
Abstract. A recent innovation in student knowledge modeling is the
replacement of static estimates of the probability that a student has guessed or
slipped with more contextual estimation of these probabilities [2], significantly
improving prediction of future performance in one case. We extend this method
by adjusting the training set used to develop the contextual models of guessing
and slipping, removing training examples where the prior probability that the
student knew the skill was very high or very low. We show that this adjustment
significantly improves prediction of future performance, relative to previous
methods, within data sets from three different Cognitive Tutors.
1 Introduction
Developing accurate models of students' knowledge as they use educational software is
valuable for many goals. First, it enables learning systems to respond more accurately to
differences in student knowledge, optimizing the amount of practice each student
receives on each skill [cf. 9]. Second, estimates of student knowledge are often a useful
component in the development of models of more complex behavioral constructs, such as


Source: Aleven, Vincent - Human Computer Interaction Institute, School of Computer Science, Carnegie Mellon University


Collections: Computer Technologies and Information Sciences