Silva, Ivanovitch Medeiros Dantas daDomingos, Elke Samantha da Silva2025-02-032025-02-032025-01-27DOMINGOS, Elke Samantha da Silva. Automação inteligente para predição do uso problemático da internet em jovens com base em indicadores físicos e aprendizado de máquina. 2025. 54 f. Trabalho de Conclusão de Curso (Bacharelado em Engenharia Mecatrônica) – Centro de Tecnologia, Universidade Federal do Rio Grande do Norte, Natal, 2025.https://repositorio.ufrn.br/handle/123456789/62406Problematic internet use among children and adolescents is a growing concern in the digital era, as it is often associated with mental health issues such as depression and anxiety. However, traditional methods for measuring this behavior typically require professional assessments, creating access barriers for many families. As an alternative, physical and fitness indicators such as posture, irregular diet, and reduced physical activity are easily accessible and can serve as proxies to identify problematic internet use in contexts where clinical assessment tools are unavailable. This study developed a predictive machine learning model using data on physical activity, behavioral, psychological, and general health parameters to detect early signs of this behavior and its severity. The results demonstrate the potential of accessible, data-driven tools that can aid in early interventions, promoting healthier digital habits and a more balanced development for children and adolescents.Uso Problemático da Internet em JovenInteligência ArtificialMachine LearningXGBoostÁrvore de DecisãobachelorThesisCNPQ::ENGENHARIAS