Abstract

Computer systems, that support learning processes, can adapt to the needs and states of a learner. The adaptation might directly address the knowledge deficits and most tutoring systems apply an adaptable learning path of that kind. Apart from a preliminary knowledge state, there are more factors, that influence education effectiveness and among those there are fluctuating emotional states. The tutoring systems may recognize or predict affective states of a learner and react to them to foster success of an educational process. This paper explores, how techniques derived from affective computing and user-centric design might be applied in intelligent tutoring systems development. An affective intervention is a modification of a standard control path or system behaviour that is a response to user’s affective state and aims at providing effective execution of a task (learning). There are several criteria for a good intervention model for an application. A system should make an affective intervention only when required and refrain from intervention otherwise. Interventions should be a natural element of an interaction with application and should be tailored to a user state. The ten step process, called AFFINT, was proposed to design appropriate affective interventions. In this paper the process is adapted to the domain of technology-based learning. The steps of the process are analyzed, providing insight into designing educational systems, that react to the recognized or predicted emotional state of a learner. The study is based both on literature review as well as it is supported with a design case study of an educational tool. The paper shows, that combining affective computing and educational systems is possible and beneficial. The paper might be interesting both for researchers, working on educational processes and supportive tools as well as for developers, aiming at designing effective tutoring systems.

Author (1)