Two Pseudo-Students: Applications of Machine Learning to Formative Evaluation

摘要

The goal of the research described here is to develop simulation programs thatcan be used for formative evaluation during the instructional design process. Such simulations are called pseudo-students because they simulate human students learning from the given instruction. However, unlike human students, pseudo-students keep a detailed trace of the learning so that the designer can discover the causes of undesirable pedagogical outcomes. For instance, one pseudo-student, psuedo-student(Sierra), helped demonstrate that many systematic arithmetic errors are caused by incomplete and poorly sequenced instruction (VanLehn, K. (1990) psuedo-students (Mind bugs: The origins of procedural misconceptions), Cambridge, MA: MIT Press). Most of these design defects would be easy to fix now that have been detected. We describe Sierra and a second pseudo-student, Cascade, which is being developed for modeling the learning of college physics. (Author) (kr)