Laughter Accelerometer-Based Detection in Natural Social Interactions
Investigating segmentation and inter-modality annotation strategies for wearable laughter detection
L. Knezevic Orbovic (TU Delft - Electrical Engineering, Mathematics and Computer Science)
H.S. Hung – Mentor (TU Delft - Pattern Recognition and Bioinformatics)
L. Li – Mentor (TU Delft - Pattern Recognition and Bioinformatics)
S. Tan – Graduation committee member (TU Delft - Interactive Intelligence)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
We propose a method for detecting laughter in spontaneous social interactions using chest-worn accelerometers. Our approach compares three segmentation strategies—padded, centered, different sliding win- dowssizesandevaluatesannotationmodalities: No Audio, Only Audio, and With Audio. Using time-domain features and Random Forests, we reach up to 0.962 macro F1-score. Longer windows and multimodal annotations improve performance and generalizability. Key features include axis-wise means, deriva- tives, and inter-axis correlations. These results support the potential of motion-based laughter detection in privacy-sensitive environments, while highlighting the importance of segment and label design.