Author :
Schuller, Bjöm ; Rigoll, Gerhard ; Lang, Manfred
Abstract :
In this paper we introduce a novel approach to human emotion recognition, based on manual computer interaction. The presented methods rely on conventional graphical input devices. Firstly, a standard mouse as used on desktop PCs, and, secondly, the interaction with touch-screens or -pads as in public information terminals, palm-top devices or tablet PCs is considered. Additionally, the gain of the integration of touch pressure information is evaluated. Four discrete emotional states are classified: irritation, annoyance, reflectiveness, and neutral affect, for use in initiative tutoring, error clarification, Internet customer personalization, and others. The optimal feature-set is discussed and ranked according to a linear discriminant analysis. A working system, using support vector machines for the classification, is tested in real-life scenarios. A performance of up to 83.2% correct assignment clearly indicates that user emotion recognition is possible without special hardware in any standard graphical user environment, independent of the underlying application
Keywords :
emotion recognition; graphical user interfaces; haptic interfaces; signal classification; support vector machines; tactile sensors; GUI manual interaction; Internet customer personalization; annoyance; discrete emotional states; emotion classification; error clarification; graphical input devices; graphical user interfaces; human emotion recognition; initiative tutoring; irritation; linear discriminant analysis; manual computer interaction; mouse; neutral affect; palm-top devices; public information terminals; reflectiveness; support vector machines; tablet PC; tactile interaction information; touch pressure information; touch-pad; touch-screen; Emotion recognition; Graphical user interfaces; Humans; Linear discriminant analysis; Mice; Network neutrality; Personal communication networks; Support vector machine classification; Support vector machines; System testing;
