Modeling Student Engagement by Means of Nonverbal Behavior and Decision Trees

Abstract

In education, student engagement refers to the degree of attention, curiosity, interest, optimism, and passion that students show when they are learning or being taught, which extends to the level of motivation they have to learn and progress in their education. This paper is intended to automatically decide whether students are interested in the class or they are not; this information was obtained from their face expressions and behavior. Five attributes are defined for evaluating: the "face" attribute, the "eyes" attribute, the "shoulders" attribute, the "mouth" attribute and finally the attribute "interested" in which the others attributes are classified in "interested" "uninterested" and "neutral". 60 instances were stored from five different students and were classified using decision trees found in Weka software, among which were used: ID3, RANDOM TREE, C4.5, BFTREE, REPTree. Applying F-Measure metric we evaluate these decision trees in order to obtain the best of them. This work is part of a bigger project.