USILaughs

A growing number of pervasive systems integrate emotion recognition capabilities with the aim of fostering and promoting human health and wellbeing. In this paper, we argue that enhancing these systems with the ability to detect laughter episodes automatically would improve their effectiveness. This is because laughter is one of the most expressive behavioral cues for positive emotions. However, the existing approaches for laughter recognition rely on the use of obtrusive devices or of video and audio cues and have thus limited applicability in real-world settings. To overcome this limitation, we evaluate the feasibility of a novel, multi-modal approach to recognize laughter episodes using physiological and body movement data gathered with unobtrusive, wrist-worn devices. To assess the performance of our method, we collect an extensive data set of laughter episodes, which we also make publicly available. Our results show that laughter episodes can be distinguished from non-laughter episodes with an accuracy of 81%. Further, we demonstrate that the signatures left by laughter episodes on physiological and body-movement data differ significantly from those caused by slightly intense motions or cognitive load tasks.