ABSTRACT

Science fiction has long predicted that technology will develop relationships and interact with humans using emotions, just like other humans do. Technologies that can use emotions in conversations with people are now becoming reality. To do so, technology needs to sense and respond to human emotions and intentions. First, technology should be capable of perception – to understand signals given by the human user, including words, quality of speech and accompanying nonverbal cues such as facial expressions, gestures and posture. The agent would then need to be able to reason about these cues and in relation to its own goals and the users. Finally, the technology needs to be able to translate its resulting decisions into suitable and emotionally rich behaviors. The chapter reviews work on each of these steps in turn: progress toward technology being able to perceive human emotional cues, reason about emotion and generate emotional cues. Finally, we discuss relevant applications for entertainment, education, health and communication.