A Differential Temporal Interestingness Measure for Identifying the Learning Behavior Effects of Scaffolding

Effective design and improvement of scaffolding in complex and open-ended learning environments, requires the ability to assess the effectiveness of a variety of scaffolding options, not only in terms of overall performance and learning, but also in terms of more subtle effects on students’ behavior and understanding. In this paper, we present a novel data mining technique that aids the analysis of scaffolding and students’ learning behaviors by identifying activity patterns that distinguish groups of students (e.g., groups that received different scaffolding and feedback during an extended, complex learning activities) by differences in both total behavior pattern usage and evolution of pattern usage over time. We demonstrate the utility of this technique through application to student activity data from a recent experiment with the Betty’s Brain learning environment and four different scaffolding conditions.