Conati C., & VanLehn, K. (1999). Teaching meta-cognitive skills: Implementation and evaluation of a tutoring system to guide self-explanation while learning from examples. In S. P. Lajoie & M. Vivet (Eds.), Artificial Intelligence in Education (pp. 297-304), Amsterdam: IOS Press.

The SE-Coach is a tutoring module designed to help students learn effectively from examples through guiding self-explanation, a meta-cognitive-skill that involves clarifying and explaining to oneself the worked out solution for a problem. The SE-Coach provides this guidance through (a) an interface that allows the student to interactively build self-explanations based on the domain-theory (b) a student model that assesses the quality of the student's explanations and the student's understanding of the example. The SE-Coach uses the assessment in the student model to elicit further self-explanation to improve example understanding. In the paper we describe how the SE-Coach evolved from its original design to the current implementation via an extensive and thorough process of iterative design, based on continuous evaluations with real students. We also present the results of the final laboratory experiment that we have performed with 56 college students. We discuss some hypotheses to explain the obtained results, based on the analysis of the data collected during the experiment.

For a PDF full article version, click here (100KB).

Note: This paper won the "best paper" award of the conference.