Keith W. Brawner, Benjamin S. Goldberg
The potential of Intelligent Tutoring Systems (ITSs) to influence learning may be greatly enhanced by the tutor’s ability to accurately assess the student’s state in real-time and then use this state as a basis to provide timely feedback or alter the instructional content. In order to maximize the ITS’ potential to influence learning, the physiological state of students needs to be captured and assessed. Electrocardiogram (ECG) and Galvanic Skin Response (GSR) data has been shown to be correlated to physiological state data, but the development of real-time processing and analysis of this data in an educational context has been limited. This article describes an experiment where nineteen participants interacted with the Cultural Meeting Trainer (CMT), a web-based cultural negotiation trainer. Metrics of mean, standard deviation, and signal energy were collected from the GSR datastream while instantaneous and average heart rate were collected from the ECG datastream using a windowing technique around important interactions. Our analysis assesses these measures across three interaction scenarios. The findings of this experiment influence the appropriateness of instructional intervention, and drive the development of real-time assessment for education.
The final publication is available at Springer via https://doi.org/10.1007/978-3-642-30950-2_10.