Web Based Keystroke Dynamics Application for Identifying Emotional State

Abstract: Emotion is one of the important features of human being that makes them different from machines. Traditionally, today‘s computer system do not incorporate any emotional exchange in the decision making process. If we could develop an emotional aware system which can interact with human involving emotions then using machines could be more effective and friendly. Conventional emotional identification methods (facial expressional analysis, voice intonation analysis, thermal imaging of the face) use intrusive, lab-based, and expensive tools which are unsuitable for real-world situations. A possible solution for emotion identification without these drawbacks is to determine user emotion by analyzing the rhythm of their typing pattern on a keyboard. This paper presents techniques to recognize the emotional state of the user through analyzing the keystroke patterns of the user.

Keywords: Affective Computing, keystroke dynamics, biometric, emotion detection