Affective computing emerged a decade ago, in order to enable intelligent interaction between humans and computers through the development of systems with more human-like computing abilities. According to its founder, Rosalind Picard, "affective computing" is computing that relates to, arises from, or deliberately influences emotions.

The main aims of researchers in the affective computing research field are those of: (a) making the interfaces between humans and computers sensitive to a human's affective state using various input modalities, and (b) adapting a computer's behavior and output according to a human's affective state. Achieving these aims is still an open challenge.

In human-human interaction, emotions can be communicated by various signals: blood chemistry, brain activity, temperature, voice, tone, face, body etc. Computers can also measure affect that is clearly expressed to them, for instance, using (a) psychological signals obtained from electromyography (EMG), (b) visual signals recorded by cameras, (c) audio signals recorded by microphones etc.

Affective computing advocates the idea that it might not be essential for machines to possess all of the emotions and skills possessed by humans. For example, the computer inside an automatic teller machine (ATM) or an airplane probably does not need to recognize emotions. However, in applications where computers take on a social role such as an "instructor'', "helper'' or even "companion'', their functionality can be enhanced by recognizing a user's emotions. Consequently, for natural and effective human-computer interaction, computers still need to look intelligent to some extent.

Systems that can sense, process, and interpret affective states have great potential in various areas of research and industry areas such as: distance education, improving drivers' safety, novel affective toys and humanoid robotics, virtual worlds, animation/synthesis of life-like agents, games, Ambient intelligence, and video conferencing.

Textbook

Rosalind Picard, Affective Computing, The MIT Press, MA, USA, 1997.

Further Reading

Scott Brave and Clifford Nass, The Media Equation: How People Treat Computers, Televisions, and New Media Like Real People and Places, Cambridge University Press, New York, NY, USA, 1996.

Scott Brave and Clifford Nass, Emotion in human-computer interaction, in The human-computer interaction handbook: fundamentals, evolving technologies and emerging applications, Julie A. Jacko and Andrew Sears, Eds., pp. 81 - 96, 2002.

Donald A. Norman, Emotional Design: Why We Love (Or Hate) Everyday Things, 2003, ISBN: 0465051359.

Marvin Minsky, The Emotion Machine: Commonsense Thinking, Artificial Intelligence, and the Future of the Human Mind, Simon & Schuster, September, 2006, ISBN: 0743276639.

Summary Written By

Hatice Gunes

Computer Vision Research Group

University of Technology, Sydney (UTS)