SmartPlay

A smartwatch software for measuring play with a data-driven, interdisciplinary approach

On playgrounds, children run, explore, and socialise. Play provides children with crucial opportunities to develop physically and socially, and is an essential right for children. However, little is known how children play and how children experience play, especially not in children with developmental/psychiatric difficulties. We aim to build a method for measuring individual differences during play, by developing a software for smartwatches that simultaneously records social behaviour, movements, locations, and heart rate via the built-in sensors in smartwatches, collects subjective experiences from children in real time during play, and integrates all these. It thus combines knowledge from Psychology/Psychiatry, Architecture, and Computer Science, capturing children’s play behaviours in relation to the surrounding environments. This will give social scientists an easy, readily applicable tool to measure play via an interdisciplinary, data-driven approach, allowing for novel research questions and interventions, and making children active “co-researchers” in defining the data about them, leading to a paradigm change. E.g., social scientists will be able to examine (i) stress levels via wearables, and relevant inter-/intra-personal factors; (ii) social connectedness (e.g., when/how long a child interacts, with whom) and enjoyment (e.g., whether a child is alone by choice or excluded); (iii) real-time experiences and built environments (e.g., use of space/playsets). Data scientists can also design algorithms to model a certain social behaviour. The codes will be released publicly on Github upon its completion. The development of this software will be published in a conference paper.

Participating organisations

Netherlands eScience Center
Leiden University
Delft University of Technology
University of Twente
Inter-Psy
Social Sciences & Humanities
Social Sciences & Humanities

Team

Jisk Attema
Programme Manager
Netherlands eScience Center
CR
Carolien Rieffe
Lead Applicant
University of Twente
MN
Maedeh Nasri
EB
Els Blijd-Hoogewys
AK
Alexander Koutamanis
Advisor
Delft University of Technology
YT
Yung-Ting Tsou

Related projects

Automated video-based movement assessment

Automated video-based movement assessment using machine learning to support personalized treatment of movement disorders

Updated 12 months ago
Finished

Related software

WEARDA

WE

WEARDA: recording wearable sensor data for human activity monitoring.

Updated 13 months ago
4 2