Learning analytics research has used both knowledge engineering and machine learning methods to model student behaviors within the context of digital learning environments. In this paper, we compare these two approaches, as well as a hybrid approach combining the two types of methods. We illustrate the strengths of each approach in the context of…

We present an inference algorithm for perturbation models based on Poisson regression. The algorithm is designed to handle unclassified input with multiple errors described by independent mal-rules. This knowledge representation provides an intelligent tutoring system with local and global information about a student, such as error classification…

Compares the knowledge content of GTE (Generic Tutoring Environment), a generic instructional knowledge base that facilitates dynamic pedagogical decision making, and PEPE, a computational framework for representing pedagogical knowledge to tailor instruction to an individual student. The courseware's interaction with the student and instructional…

Considers claims regarding GTE (Generic Tutoring Environment) and describes how instructional strategies are represented in Eon, an authoring tool for intelligent tutoring systems. Highlights include comparisons of GTE with other formalisms; intended audiences; representing instructional expertise; tradeoffs between generality and inferencing…