By Xiaohong Zhao and Cristina Conati
Educational games can be highly entertaining, but studies have shown that they are not always effective for learning.
To enhance the effectiveness of educational games, we propose intelligent pedagogical agents that can provide individualized instruction integrated with the entertaining nature of these systems. We have embedded one such animated pedagogical agent into the electronic educational game Prime Climb. The agent's behavior is guided by a probabilistic student model that performs on-line assessment of student knowledge.
To do knowledge assessment, the student model accesses a student's game actions. By representing through a Bayesian network, the probabilistic relations between these actions and the corresponding student's knowledge, the student model assesses the evolution of this knowledge during game playing.
We performed an empirical study to test the effectiveness of both the student model and the pedagogical agent. We will present the results from the study, which give strong support to the effectiveness of our approach.