Abstract: Emotion recognition technology is currently being developed with the aim of improving the quality of human-computer interaction. Research in this domain emphasises solving the technical difficulties involved, through the design of ever more complex recognition algorithms. But fundamental questions about the use of such technology remain neglected. Can it really improve human-computer interaction? For which types of application is it suitable? How is it best implemented? These questions are not being addressed because of the current state of the technology: the systems are simply not yet good enough to be implemented in realistic applications. This research will overcome this barrier by simulating the capabilities of future emotion recognition technology using the 'Wizard of Oz' approach, which proved so helpful in the early development of systems using speech recognition technology. The research will explore the use of emotion recognition technology from a user's perspective. It will empirically test assumptions about human behaviour which underlie the use of such technology. It will test the impact of emotion recognition on measures of usability and user satisfaction. Such research is vital if emotion recognition technology at the user interface is ever to provide tangible benefits to real users.

Aims and objectives:
The research aims to evaluate the potential for emotion recognition technology to improve the quality of human-computer interaction.

The specific objectives of the research are:
1) to establish the extent to which people will naturally express emotions when they know they are interacting with an emotion-detecting computer.
2) to identify the conditions under which the application of emotion detection can lead to improvements in subjective and/or objective measures of system usability.
3) to provide Human Factors guidelines on the deployment of emotion recognition technology which can help the developers of such technology to meet the needs of real users.

Keywords: affective computing, human-computer interaction, human factors, emotion recognition