Predicting Social Dynamics in Child-Robot Interactions with Facial Action Units
van Eijndhoven,Kyana Wiltshire,Travis Vogt,Paul
van Eijndhoven,Kyana
Wiltshire,Travis
Vogt,Paul
Abstract
We examine the extent to which task engagement, social engagement, and social attitude in child-robot interaction can be predicted on the basis of Facial Action Unit (FAU) intensity. The analyses were based on child-robot and child-child interaction data from the PInSoRo dataset [1]. We applied Logistic Regression, Naive Bayes, and Probabilistic Neural Networks to these data. Results indicated that FAU intensities have potential to predict social dynamics in child-robot interactions (average balanced accuracy scores up to 84%), and illustrate a difference in behavior of children towards other children when compared to their interaction with robots.
Description
Date
2020-03-23
Journal Title
Journal ISSN
Volume Title
Publisher
ACM, New York
Research Projects
Organizational Units
Journal Issue
Keywords
Human-Robot Interaction, Social Dynamics, Facial Action Coding System (FACS), Neural Network, Machine Learning, robot
Citation
van Eijndhoven, K, Wiltshire, T & Vogt, P 2020, Predicting Social Dynamics in Child-Robot Interactions with Facial Action Units. in HRI 2020 - Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction. ACM/IEEE International Conference on Human-Robot Interaction, ACM, New York, pp. 502-504. https://doi.org/10.1145/3371382.3378366