Emotional characterization of children through a learning environment using learning analytics and AR-Sandbox

Abstract

Identifying emotions experienced by students in a learning environment contributes to measuring the impact when technologies such as augmented reality (AR) are implemented in the educational field. The most frequent methods for collecting emotional metrics are questionnaires, surveys, and observations, but each of these processes lacks objectivity and veracity. For this reason, this study proposes, develops and tests a learning analytics scheme, based on the density-based spatial clustering of applications with noise algorithm, as a clustering technique with time series analysis, using the brain- computer interface device, Emotiv EPOC, as a way to collect emotional metrics. The above, in order to perform emotional behavior characterization by using AR in a learning environment through AR-Sandbox. The proposed method shows a clear inclination in the tendency of each emotion in each cluster, allowing classification of children during their interaction with the immersive environment, as well as the ability to distinguish each group of students.