Deriving Association between Student Comprehension and Facial Expressions using Class Association Rule Mining
The scope of this study was to discover the association between facial expressions of students in an academic lecture and the level of comprehension shown by their expressions. This study focused on finding the relationship between the specific elements of learner’s behavior for the different emotional states and the relevant expression that could be observed from individual students. The experimentation was done through surveying quantitative observations of the lecturers in the classroom in which the behavior of students are recorded and were statistically analyzed. The main aim of this paper is to derive association rules that represent relationships between input conditions and results of domain experiments. Hence the relationship between the physical behaviors that are linked to emotional state with the student’s comprehension is being formulated in the form of rules. We present Predictive Apriori algorithm that is able to find all valid class association rules with high accuracy. The rules derived by Predictive Apriori are pruned by objective and subjective measures.
