Predicting Social Dynamics in Child-Robot Interactions with Facial Action Units

Kyana van Eijndhoven; Travis Wiltshire; Paul Vogt

doi:10.1145/3371382.3378366

Predicting Social Dynamics in Child-Robot Interactions with Facial Action Units

Kyana van Eijndhoven^*
, Travis Wiltshire
, Paul Vogt

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

2 Citations (Scopus)

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.

Original language	English
Title of host publication	HRI 2020 - Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction
Publisher	ACM, New York
Pages	502-504
Number of pages	3
ISBN (Electronic)	9781450370578
DOIs	https://doi.org/10.1145/3371382.3378366
Publication status	Published - 23 Mar 2020

Publication series

Name	ACM/IEEE International Conference on Human-Robot Interaction
ISSN (Electronic)	2167-2148

Keywords

Human-Robot Interaction
Social Dynamics
Facial Action Coding System (FACS)
Neural Network
Machine Learning
robot

Access to Document

10.1145/3371382.3378366

Cite this

@inproceedings{055a65f35ec448cd921691a7b638409d,

title = "Predicting Social Dynamics in Child-Robot Interactions with Facial Action Units",

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.",

keywords = "Human-Robot Interaction, Social Dynamics, Facial Action Coding System (FACS), Neural Network, Machine Learning, robot",

author = "\{van Eijndhoven\}, Kyana and Travis Wiltshire and Paul Vogt",

year = "2020",

month = mar,

day = "23",

doi = "10.1145/3371382.3378366",

language = "English",

series = "ACM/IEEE International Conference on Human-Robot Interaction",

publisher = "ACM, New York",

pages = "502--504",

booktitle = "HRI 2020 - Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction",

}

Predicting Social Dynamics in Child-Robot Interactions with Facial Action Units. / van Eijndhoven, Kyana ; Wiltshire, Travis; Vogt, Paul.
HRI 2020 - Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction. ACM, New York, 2020. p. 502-504 (ACM/IEEE International Conference on Human-Robot Interaction).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Predicting Social Dynamics in Child-Robot Interactions with Facial Action Units

AU - van Eijndhoven, Kyana

AU - Wiltshire, Travis

AU - Vogt, Paul

PY - 2020/3/23

Y1 - 2020/3/23

N2 - 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.

AB - 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.

KW - Human-Robot Interaction

KW - Social Dynamics

KW - Facial Action Coding System (FACS)

KW - Neural Network

KW - Machine Learning

KW - robot

UR - https://www.scopus.com/pages/publications/85083192756

U2 - 10.1145/3371382.3378366

DO - 10.1145/3371382.3378366

M3 - Conference contribution

T3 - ACM/IEEE International Conference on Human-Robot Interaction

SP - 502

EP - 504

BT - HRI 2020 - Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction

PB - ACM, New York

ER -

Predicting Social Dynamics in Child-Robot Interactions with Facial Action Units

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Cite this