Individualizing self-explanation support for ill-defined tasks in constraint-based tutors

We present the first phase of a project with the goal of developing a general model of self-explanation support, which could be used in constraint-based tutors for both well- and ill-defined domains. We studied how human tutors provide additional support to students learning with an existing intelligent tutoring system designed to help students learn an ill-defined task (database modeling using the ER model). Although the tutors were not given specific instructions to facilitate self-explanation, there were instances when self-explanation support was provided. Analysis of these interactions indicates that they have helped the students to improve their understanding of database design. These findings will serve as the basis for defining the self-explanation model. We also discuss directions for future wor