Identifying Emotional States using Keystroke Dynamics.pdfVIP

CHI 2011 • Session: Emotional States May 7–12, 2011 • Vancouver, BC, Canada Identifying Emotional States using Keystroke Dynamics Clayton Epp, Michael Lippold, and Regan L. Mandryk Department of Computer Science, University of Saskatchewan 176 Thorvaldson Bldg., 110 Science Place, Saskatoon, SK, S7N5C9, Canada clayton.epp@usask.ca, mike.lippold@usask.ca, regan@cs.usask.ca ABSTRACT and second, a set of techniques for adapting user interfaces The ability to recognize emotions is an important part of and system behavior based on contextual information. building intelligent computers. Emotionally-aware systems User context includes information such as the user’s would have a rich context from which to make appropriate decisions about how to interact with the user or adapt their location, situation, or expertise, but one often ignored type system response. There are two main problems with current of context that could radically change our computer interactions is the user’s emotional state. If a user of a system approaches for identifying emotions that limit their applicability: they can be invasive and can require costly safety-critical application was frustrated or distracted, it equipment. Our solution is to determine user emotion by could dangerously affect their performance. If a user of an analyzing the rhythm of their typing patterns on a standard