Using Machine Learning to Assess the Impact of Harsh Violent Discipline on Children and Adolescents in Low- and Middle-Income Countries: A Comparative Analysis Focusing on Its Relationship with Disabilities

Milena S. Barreira, Ariane B. da Silva, Hasheem Mannani, Cristiane Nobre

2025

Abstract

Children’s exposure to violence has long been a social and cultural concern, manifesting in various forms across societies. According to UNICEF, approximately 300 million children worldwide, aged 2 to 4, experience regular violent discipline from caregivers, with around 250 million subjected to physical punishment. This study leverages data from the Multiple Indicator Cluster Survey to investigate the prevalence of severe violent discipline among children with and without disabilities in 54 low- and middle-income countries. Using machine learning algorithms, including Decision Tree, Random Forest, XGBoost, Support Vector Machine (SVM), and Neural Networks, the analysis revealed that SVM outperformed other models, achieving the highest precision, recall, and F1-score (with values of 78% and 80% for the violence and non-violence classes, respectively). The results highlighted an increase in severe disciplinary violence correlated with the presence of disabilities, particularly in contexts involving the domain of ‘controlling behavior’.

Paper Citation

in Harvard Style

Barreira M., B. da Silva A., Mannani H. and Nobre C. (2025). Using Machine Learning to Assess the Impact of Harsh Violent Discipline on Children and Adolescents in Low- and Middle-Income Countries: A Comparative Analysis Focusing on Its Relationship with Disabilities. In Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF; ISBN 978-989-758-731-3, SciTePress, pages 161-172. DOI: 10.5220/0013184500003911

in Bibtex Style

@conference{healthinf25,
author={Milena Barreira and Ariane B. da Silva and Hasheem Mannani and Cristiane Nobre},
title={Using Machine Learning to Assess the Impact of Harsh Violent Discipline on Children and Adolescents in Low- and Middle-Income Countries: A Comparative Analysis Focusing on Its Relationship with Disabilities},
booktitle={Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF},
year={2025},
pages={161-172},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013184500003911},
isbn={978-989-758-731-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF
TI - Using Machine Learning to Assess the Impact of Harsh Violent Discipline on Children and Adolescents in Low- and Middle-Income Countries: A Comparative Analysis Focusing on Its Relationship with Disabilities
SN - 978-989-758-731-3
AU - Barreira M.
AU - B. da Silva A.
AU - Mannani H.
AU - Nobre C.
PY - 2025
SP - 161
EP - 172
DO - 10.5220/0013184500003911
PB - SciTePress