Knowledge Engineering for Affective Bi-Modal Interaction in Mobile Devices

This paper focuses on knowledge engineering for the development of a system that provides affective interaction in mobile devices. The system bases its inferences about users' emotions on user input evidence from the keyboard and the microphone of the mobile device. For this purpose different experimental studies have been conducted with the participation of mobile users and human experts. The experiments' aim was twofold. They aimed at revealing the criteria that are taken into account in each mode for emotion recognition as well as their weight of importance. The results of the studies are further used for the application of a multi-criteria decision making model.