• University: Universidade Nova de Lisboa
  • Authors:  Jorge Calado, Fernando Luís-Ferreira, Joao Sarraipa, Ricardo Jardim-Goncalves

Abstract: Some of the biggest problems tackling Higher Education Institutions (HEI) are student’s drop-out and academic disengagement. Physical or psychological disabilities, social-economic or academic marginalization, and emotional and affective problems, are some of the factors that can lead to it. This problematic is worsened by the shortage of educational resources that can bridge the communication gap between the faculty staff and the affective needs of these students. In this paper, we present a framework capable of collecting analytic data, from an array of emotions, affects and behaviours, acquired either by human observations, like a teacher in a classroom or a psychologist, or by electronic sensors and automatic analysis software, such as eye tracking devices, emotion detection through automatic facial expression recognition software, among others. This framework compiles the gathered data in an ontology, and will be able to extract patterns outliers via machine learning, enabling the profiling of the students in critical situations, such as disengagement, attention deficit, drop-out, and other sociological issues, setting real time alerts when these profiles are detected. The goal is that, by providing insightful real time cognitive data and allowing the profiling of the student’s problems, a faster personalized response to help the student is enabled, allowing academic performance improvements.