Twenty-fifth International Conference on Learning

Abstract

Despite the progresses made so far, modern e-learning and distance learning systems suffer severe lack of human-like interaction with their human users and responsiveness to them: the typical system is irresponsive to the affective state of the user while even an inadequate human tutor will respond to it and even adapt his/her instruction accordingly. In an attempt to address this problem, this paper presents the design of a digital system that integrates affective assessment in a real-world distance learning scenario. The proposed system uses modern affect theory results along with state-of-the-art technologies in order to (i) “sense” or “gauge” the affective state of a remote class of learners, while they participate in a distance learning course, either synchronous or asynchronous, and (ii) provide feedback to the human participants at three levels: to the individual learner (for self-reflection purposes), to the peer learners and to the class tutor. This is achieved through intuitive, easy to grasp digital visualization of the dominant affect or “temperature” of the online (remote) class, presented on the computer screens of the participants and updated periodically along the duration of the distance learning session. The solutions investigated involve either self-reporting of the user affect or state (“explicit” case) through wearable devices and gestures, or fully automated affect recognition (“implicit” case) through fusion of a number of “experts” (monitored features or physiological parameters of the learner) that will feed a decision-making algorithm after suitable processing. System development, test, adjustment and evaluation issues are also discussed.