Identifying psychological trauma among Syrian refugee children for early intervention
Analyzing digitized drawings using machine learning
Abstract
Nearly 5.6 million Syrian refugees have been displaced by the country’s civil war, of which roughly half are children. A digital analysis of features in children’s drawings potentially represents a rapid, cost-effective, and non-invasive method for collecting information about children’s mental health. Using data collected from free drawings and self-portraits from 2480 Syrian refugee children in Jordan across two distinct datasets. We use the Least Absolute Shrinkage and Selection Operator (LASSO) machine-learning techniques to understand the relationship between psychological trauma among refugee children and digitally coded features of their drawings. We find that children’s drawing features retained using LASSO are consistent with historical correlations found between specific drawing features and psychological distress in clinical settings. We then use drawing features within LASSO to predict exposure to violence and refugee integration into host countries, with findings consistent with anticipated associations. Results serve as a proof-of-concept for the potential use of children’s drawings as a diagnostic tool in human crisis settings.
This is an output of the Gender and Adolescence: Global Evidence (GAGE) programme
Citation
Baird, S., Panlilio, R., Seager, J., Smith, S. and Wydick, B. (2022) ‘Identifying psychological trauma among Syrian refugee children for early intervention: Analyzing digitized drawings using machine learning’ Journal of Development Economics 156: 102822. https://doi.org/10.1016/j.jdeveco.2022.102822.