Aplicação de Ciência de Dados em um Ambiente Virtual de Aprendizagem: um estudo de caso na disciplina de Programação Orientada a Objetos

Abstract

This paper presents an analysis of student performance in the subject of object-oriented programming using descriptive models based on data science techniques at a public higher education institution in the municipality of Russas in the state of Ceara.´ The aim was to categorize students into performance groups, identify learning profiles and recommend specific content. Classification rules were applied to group students into categories such as good, fair, alert and critical. In addition, outliers were identified and removed to ensure the accuracy of the results. The analysis revealed patterns of behavior and performance, allowing for more accurate recommendations for educational support. It is concluded that the proposed model contributes significantly to improving learning support.