Affect-awareness framework for intelligent tutoring systems

The paper proposes a framework for construction of Intelligent Tutoring Systems (ITS), that take into consideration student emotional states and make affective interventions. The paper provides definitions of `affect-aware systems´ and `affective interventions´ and describes the concept of the affect-awareness framework. The proposed framework separates emotion recognition from its definition, processing and making decisions on interventions. The components of the proposed framework were described, including trustworthiness model and affect-aware control mechanisms, and a case study of the proposed framework implementation in GERDA Intelligent Tutoring System was also presented. Presented evidence allows to state, that affect-awareness framework allows to reduce the risk of unnecessary and disturbing application intervention and improves application adaptability and trustworthiness.