Affective laughter expressions from body movements

• Main Authors: Cu, Jocelynn, Luz, Ma Beatrice L., Nocum, McAnjelo D., Purganan, Timothy Jasper, Wong, Wing San
• Format: text
• Published: Animo Repository 2017
• Subjects: Human activity recognition; Pattern recognition systems; Laughter > Data processing; Emotion recognition; Computer Sciences
• Online Access: https://animorepository.dlsu.edu.ph/faculty_research/1469; https://animorepository.dlsu.edu.ph/context/faculty_research/article/2468/type/native/viewcontent/978_3_319_60675_0_12.html
• Institution: De La Salle University

The main goal of this study is to classify affective laughter expressions from body movements. Using a non-intrusive Kinect sensor, body movement data from laughing participants were collected, annotated and segmented. A set of features that include the head, torso, shoulder movements, as well as the positions of the right and left hands, were used by a decision tree classifier to determine the type of emotions expressed in the laughter. The decision tree classifier performed with an accuracy of 71.02% using a minimum set of body movement features. © Springer International Publishing AG 2017.