Decision Tree for Tracking Learner's Emotional State Predicted from His Electrical Brain Activity

This paper proposes the use of machine learning techniques to build an efficient learner's emotional transition diagram transition. For information Extraction tasks, we led an experimentation in which we exposed a group of 17 learners to a series of pictures from the International Affective Picture System (IAPS). Decision tree classifier has demonstrated the best ability to learn model structure from data collected. Among the emotions involved in learning and according to the picture from IAPS and the current emotional state, we drew up the transition diagram. Our model aims to improve the task of predicting the emotional state in an Intelligent Tutoring System and achieve a prediction accuracy of 63.11%. These results suggest that the implementation of the decision tree algorithm in the intelligent tutoring system we are developing improves the ability for an ITS to track the learners emotional states.