Evaluating a Decision-Theoretic Approach to Tailored Example Selection
Kasia Muldner, Cristina Conati
We present the formal evaluation of a framework that helps students learn from analogical problem solving, i.e., from problem-solving activities that involve worked-out examples. The framework incorporates an innovative example-selection mechanism, which tailors the choice of example to a given student so as to trigger studying behaviors that are known to foster learning. This involves a two-phase process based on 1) a probabilistic user model and 2) a decision-theoretic mechanism that selects the example with the highest overall utility for learning and problem-solving success. We describe this example-selection process and present empirical findings from its evaluation.