Automatic Recognition of Experienced Emotional State from Body Movement
Published in International Conference on Human Computer Interaction, 2021
Voigt-Antons, J.-N., Devaikin, P. & Kojić, T.
This work examines whether emotions experienced during interaction can be inferred from whole-body kinematics. Using pose and velocity features captured from motion sensors, we train classifiers to distinguish arousal and valence states validated by self-reports. The models reach robust performance across tasks, indicating the potential of movement-based affect sensing for interactive systems and XR experiences.
Recommended citation: Voigt-Antons, J.-N., Devaikin, P. & Kojić, T. (2021, July). Automatic Recognition of Experienced Emotional State from Body Movement. Paper presented at the International Conference on Human-Computer Interaction. https://doi.org/10.1007/978-3-030-78462-1_49