Real-Time Assessment of Student State

"Our proposed Hybrid Tutor provides a real-time assessment of student state that is richer than current approaches. It includes performance-based measures of actions and choices during a realistic simulation, as well as knowledge-based measures of studentplans and explanations. It includes latency and self-assessment measures that provide information for an affect model of certainty and confidence. A Bayesian analysis takes these various measures and forms a student state model consisting of knowledge,skills, and affect. The student state model is continually updated, and influences the tutor's strategies so that it customizes interactions and instruction to the individual student.The ITS will be developed so that the main components (student model, domain knowledge, and tutor strategies) are reusable for other tutoring applications. The ITS will be plug-compatible with existing PC-based simulations through the use of softwareconnectors. This will allow the tutor opportunities to gather input from the student and provide feedback and explanations. Evaluation of student actions in the simulation is performed by ontological reasoning. This reasoning is supported by a domainknowledge representation, a domain specific knowledge base backed by a standard upper ontology. Thus the tutor has an expert level active knowledge of domain concepts, rules and solutions. We expect that the proposed approach will provide improved training ef