Knowledge Engineering for Affective Bi-Modal Human-Computer Interaction

This paper presents knowledge engineering for a system that incorporates user stereotypes as well as a multi criteria decision making theory for affective interaction. The system bases its inferences about students’ emotions on user input evidence from the keyboard and the microphone. Evidence form these two modes is combined by a user modelling component underlying the user interface. The user modelling component reasons about users’ actions and voice input and makes inferences in relation to their possible emotional states. The mechanism that integrates the inferences form the two modes has been based on the results of two empirical studies that were conducted in the context of requirements analysis of the system. The evaluation of the developed system showed significant improvements in the recognition of the emotional