Use of Clustering for Evaluation of Educational Performance and Management Support in Investment Areas
Abstract
The National Education Plan (PNE) defines goals and indicators that relate to education, and managers of federated entities in Brazil must address them. In the case of the municipal manager, observing the practices of municipalities with similar characteristics that have achieved better results in the PNE indicators can help in the decision on the use of the resources. This work proposes an innovative method with two stages: (1) Clusterization of Brazilian municipalities with unsupervised learning based on the sociodemographic metrics; (2) Comparison of educational metrics between a municipality and the other municipalities of its cluster. This study shows an improvement in the Silhouette Coefficient, confirming that our method created more cohesive clusters. To exemplify this approach, we analyze the Indicator 1A of Goal 1 of the PNE for the city of Salvador. We observed that the good results for some educational metrics did not reflect a significant improvement in the assessed PNE indicator.
References
Arthur, D. and Vassilvitskii, S. (2006). k-means++: The advantages of careful seeding. Technical Report 2006-13, Stanford InfoLab. Bandeira, L. F. and Reyes Junior, E. (2021).
Programa minha casa minha vida (2012-2016): análise da eficiência relativa dos municípios brasileiros na execução de programas federais. Revista de Administração Pública,55:309–330.
Brasil (2014). Lei nº 13.005, de 25 de junho de 2014. Aprova o plano nacional de educação - pne e dá outras providências. Diário Oficial [da] República Federativa do Brasil.
Clow, D. (2013). An overview of learning analytics. Teaching in Higher Education, 18(6):683–695.
Gan, G. and Ng, M. K.-P. (2017). k-means clustering with outlier removal. Pattern Recognition Letters, 90:8–14.
Gordia, A. P. e. a. (2010). Variáveis comportamentais e sociodemográficas estão associadas ao domínio psicológico da qualidade de vida de adolescentes. Chinese Science Bulletin, 28(1):29–35.
Greco, S., Figueira, J., and Ehrgott, M. (2016). Multiple Criteria Decision Analysis: State of the Art Surveys. Springer.
Gutiérrez, F., Seipp, K., Ochoa, X., Chiluiza, K., De Laet, T., and Verbert, K. (2020). Lada: A learning analytics dashboard for academic advising. Computers in Human Behavior, 107:105826.
Herodotou, C., Rienties, B., Boroowa, A., Zdrahal, Z., and Hlosta, M. (2019). A large-scale implementation of predictive learning analytics in higher education: the teachers’ role and perspective. Educational Technology Research and Development, 67(5):1273– 1306.
IBGE (2022). Áreas territoriais. Disponível em: [link].
Jordan, M. I. and Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science, 349(6245):255–260.
MEC (2022). Pne em movimento. Disponível em: http://simec.mec.gov.br/pde/grafico_pne.php.
Montgomery, D. C. and Runger, G. C. (2018). Applied Statistics and Probability for Engineers. John wiley & sons.
MP-SC (2022). Relatório de monitoramento do plano municipal de educação. Disponível em: [link].
PNAD Contínua, I. (2022). Pnad contínua - pesquisa nacional por amostra de domicílios contínua.
Rousseeuw, P. J. (1987). Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20:53–65.
Silva, W. D., Pereira, S. S. L., Pereira, D. S., and COSTA, M. (2021). Um sistema baseado em machine learning para apoio à decisão no gerenciamento de produção apícola. Embrapa Amazônia Oriental-Artigo em periódico indexado (ALICE).
TCE-SC (2022). Espaço tce educação. Disponível em: https://servicos.tce.sc.gov.br/tceeducacao/#acompanhamento.
Todos pela Educação (2022). Observatório do plano nacional de educação. Disponível em: https://www.observatoriodopne.org.br.
Zapparolli, L., Stiubiener, I., Braga, J., and Pimentel, E. (2017). Aplicando técnicas de business intelligence e learning analytics em ambientes virtuais de aprendizagem. Simpósio Brasileiro de Informática na Educação, 28(1):536–545.
