Publicação

Artificial Intelligence for e-Government: A View on Children’ Welfare

Ver documento

Detalhes bibliográficos
Resumo:This thesis aims to perform a holistic investigation concerning the use of artificial intelligence advance techniques in predicting children in danger of abuse or neglect. A dataset containing over 55322 cases from the Portuguese National Commission for the Promotion of the Rights and Protection of Children and Youth (CNPCJ) was collected and trained to uncover the patterns and additional findings. This research uses machine learning classification models to unveil the model with highest accuracy and robustness in the use predictive analytics in the children’s’ welfare field. This approach will allow social security services to understand the impact of underlying factors for further improvement of their services. Finally, this study develops a random forest predictive model to forecast children in risk, with an accuracy of 84.5%.
Autores principais:Caria, Tânia Filipa Medeiros
Assunto:Artificial Intelligence Machine Learning e-Government Child maltreatment Predictive Analytics SDG 3 - Good health and well-being SDG 9 - Industry, innovation and infrastructure SDG 11 - Sustainable cities and communities SDG 16 - Peace, justice and strong institutions
Ano:2023
País:Portugal
Tipo de documento:dissertação de mestrado
Tipo de acesso:acesso aberto
Instituição associada:Universidade Nova de Lisboa
Idioma:inglês
Origem:Repositório Institucional da UNL
Descrição
Resumo:This thesis aims to perform a holistic investigation concerning the use of artificial intelligence advance techniques in predicting children in danger of abuse or neglect. A dataset containing over 55322 cases from the Portuguese National Commission for the Promotion of the Rights and Protection of Children and Youth (CNPCJ) was collected and trained to uncover the patterns and additional findings. This research uses machine learning classification models to unveil the model with highest accuracy and robustness in the use predictive analytics in the children’s’ welfare field. This approach will allow social security services to understand the impact of underlying factors for further improvement of their services. Finally, this study develops a random forest predictive model to forecast children in risk, with an accuracy of 84.5%.