Intelligent tutoring systems for skill acquisition
Derek Tannell Green · UA Campus Repository (The University of Arizona) · 2011
Throughout history education has been restricted to a relatively small percentage of the world's population. The cause can be attributed to a number of factors; how- ever, it has been chiefly due to excessive cost. As we enter the information age it becomes conceivable to make education freely available to anyone, anywhere, any- time. The Intelligent Tutoring System is an automated teaching system designed to improve through experience, eventually learning to tailor its teaching to perfectly match each individual student's needs and preferences. In this dissertation we describe a template which we use for building problem-oriented skill teaching intelligent tutoring systems based on a Dynamic Bayes network framework. We present two case studies in which the template is adapted to very different teaching domains, documenting in each case the process of building, training, and testing the resulting ITS. In both case studies, the performance of the ITS is validated through human subject experiments. The results of these studies show that our template is a viable technique for designing ITSs that teach in skill based domains. We also show that, while conducting artificial intelligence research on the design of an ITS and collecting data for use in that regard, we can concurrently run educational research experiments. We find that the two are quite inextricably tied and that showing good general results regarding the performance of the ITS is not sufficient; a strong understanding of the experience of the students is also required. We report some interesting results covering the effect of choice in learning and a gender bias that shows up in our tutoring system.