A Probabilistic Relational Student Model for Virtual Laboratories

Abstract

We have developed an intelligent tutoring system coupled with a virtual laboratory, which constitute a semi-open learning environment. This environment provides the student with the opportunity to learn through exploration within a virtual laboratory, while achieving the expected learning objectives. The key element of this environment is a novel representation for the student model based on probabilistic relational models. This student model has several advantages: flexibility, user adaptability, high modularity and facilities for model construction for different scenarios. The model keeps track of the students' knowledge at different levels of granularity, combining the performance and exploration behavior in several experiments, to decide the best way to guide the student in following experiments, and to re-categorize the students based on the results. We have implemented a tutor for a virtual robotics laboratory, and evaluated the system with an initial group of 20 students. The results show that students who explore the virtual environment with the help of the tutor have a better academic skills, and also that the predictions of the student model are generally accurate.