Knowledge tracing (KT) models have been a commonly used tool for tracking students' knowledge status. Recent advances in deep knowledge tracing (DKT) have demonstrated increased performance for knowledge tracing tasks in many datasets. However, interpreting students' states on single knowledge components (KCs) from DKT models could be challenging…

Bayesian Knowledge Tracing (BKT) is a probabilistic model of a learner's state of mastery for a knowledge component. The learner's state is a "hidden" binary variable updated based on the correctness of the learner's responses to questions corresponding to that knowledge component. The parameters used for this update are inferred/learned…

Various researchers have associated meaningful problem solving with methods guided directly by a conceptual knowledge base. By contast, a meaningless solving course, or sequence of operations, is essentially independent of the solver's conceptual understanding of the problem under consideration. This paper is the first to document a meaningless,…

Reform efforts in mathematics aim to increase conceptual understanding, an aim that can be supported through concept maps. This study compared the conceptual knowledge of function held by college students in reform and traditional calculus sections at a large state university. Fourteen students from reform sections and 14 from traditional sections…