Adaptive virtual reality game system for personalized problem-based learning
Ying Gina Tang, Sachin S. Shetty · 2011
There is an increasing awareness among engineering educators that more and more students are not able to achieve learning successfully in a “one-size-fit-all” model where a set of instructions are provided identically to every student in a given class. This paper addresses this challenge by offering an intelligent virtual reality game system that not only immerses students in an attractive and engaging learning environment, but also imparts essential metacognitive and problem-solving skills tailored to student individual needs. More specifically, a mathematical Bayesian Network model is designed to characterize the probabilistic casual relationship between student acquisition of a problem solution and his/her mastery of facts and concepts pertinent to the problem, from which the system infer students' individual knowledge states. During the learning session where students are involved in the problem-solving process, the system would analyze players' interactions with three already in-place metacognitive strategies (i.e., What I Know-What I Want to Know - What I Have Solved, Think-Aloud-Share-Solve, and Road Map), and dynamically map the students' responses to a set of question prompts necessary in correcting their specific misconceptions and overcoming impasses.