Affective state-based framework for e-learning systems

Abstract

Virtual learning and education have become crucial during the COVID19 pandemic, which has forced a rethink by teachers and educators into designing online content and the indirect interaction with students. In an face-to-face class, some visual cues help the teacher recognize the engagement level of students, while the main weakness of the online approach is the lack of feedback that the teacher has about the learning process of the students. In this paper, we introduce a novel framework able to track the learning states, or LS, of the students while they are watching a piece of knowledge-based content. Specifically, we extract four learning states: Interested, Bored, Confused or Distracted. Finally, to demonstrate the system’s capability, we collected a reduced database to analyze the affective state of the subjects. From these preliminary results, we observe abrupt changes in the LS of the audience when there are abrupt changes in the narrative of the video, indicating that well-structured and bounded information is strongly related with the learning behaviour of the students.