The Impact of High Dropout Rates in a Large Public Brazilian University - A Quantitative Approach Using Educational Data Mining

Laci Mary Barbosa Manhães, Sérgio Manuel Serra da Cruz, Geraldo Zimbrão

2014

Abstract

This paper uses educational data mining techniques to identify the variables that can help educational managers to detect students that present low performance or are in risk to dropout their undergraduate education. We investigated real world academic data of students of the largest Public Federal Brazilian University. We established three categories of students with different academic trajectory in order to investigate their performance and the dropout rates. This study shows that even analyzing three different classes of 14.000 students it was possible to have a global precision above 80% for several classification algorithms. The results of Naïve Bayes model were used to support the quantitative analysis. In this work, we stress that even few differences between the three classes of students that can be perceived on the basis of qualitative information.

References

  1. Baker, R. S. J. D., Yacef, K., 2009. The state of educational data mining in 2009: A review and future visions. J. of Educational Data Mining 1.1, 3-17.
  2. Baker, R., Isotani, S., Carvalho, A., 2011. Mineração de Dados Educacionais: Oportunidades para o Brasil. Revista Brasileira de Informática na Educação.
  3. Dekker, G., Pechenizkiy, M., Vleeshouwers, J., 2009. Predicting Students Drop Out: A Case Study. In Proceedings of the int. Conf. on Educational Data Mining. Cordoba, Spain, 41-50.
  4. Huang, S., 2011. Predictive Modeling and Analysis of Student Academic Performance in an Engineering Dynamics Course. Ph.D. Thesis, Utah State University, Logan, USA.
  5. Kotsiantis, S., Pierrakeas, C., Pintelas, P., 2003. Preventing student dropout in distance learning using machine learning techniques. KES, eds. V. Palade, R. Howlett & L. Jain, Springer, v. 2774 LNCS, pp. 267-274, 1087- 6545.
  6. Lobo, M. B. C. M., 2011. Panorama da evasão no ensino superior brasileiro: aspectos gerais das causas e soluções. Instituto Lobo & Associados Consultoria.
  7. Lykourentzou, I. et al., 2009. Dropout prediction in elearning courses through the combination of machine learning techniques, Computers & Education, v. 53, N. 3, pp. 950-965.
  8. Manhães, L. M. B., Cruz, S. M. S., Costa, R. J. M, Zavaleta, J. and Zimbrão. Identificação dos Fatores que Influenciam a Evasão em Cursos de Graduação através de Sistemas Baseados em Mineração de Dados: Uma abordagem Quantitativa. In: VIII Simpósio Brasileiro de Sistemas de Informação (SBSI 2012) (São Paulo, Brasil, May 16-18, 2012), 468-479.
  9. MEC, 1997. Ministério da Educação e Cultura. Diplomação, Retenção e Evasão nos Cursos de Graduação em Instituições de Ensino Superior Públicas.
  10. Pal, S., 2012. Mining educational data to reduce dropout rates of engineering students. International Journal of Information Engineering and Electronic Business (IJIEEB), 4(2), 1.
  11. Romero, C., Ventura, S., 2010. Educational Data Mining: A Review of the State of the Art, Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions, v.40, n.6, 601-618.
  12. Romero, C., Ventura, S., 2013. Data Mining in Education. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, In Press. v. 3, n. 1, 12-27.
  13. Soares, I. S. 2006. Evasão, retenção e orientação acadêmica: UFRJ. In: Anais do XXXIV COBENGE - Congresso Brasileiro de Ensino de Engenharia.
Download


Paper Citation


in Harvard Style

Mary Barbosa Manhães L., Manuel Serra da Cruz S. and Zimbrão G. (2014). The Impact of High Dropout Rates in a Large Public Brazilian University - A Quantitative Approach Using Educational Data Mining . In Proceedings of the 6th International Conference on Computer Supported Education - Volume 3: CSEDU, ISBN 978-989-758-022-2, pages 124-129. DOI: 10.5220/0004958601240129


in Bibtex Style

@conference{csedu14,
author={Laci Mary Barbosa Manhães and Sérgio Manuel Serra da Cruz and Geraldo Zimbrão},
title={The Impact of High Dropout Rates in a Large Public Brazilian University - A Quantitative Approach Using Educational Data Mining},
booktitle={Proceedings of the 6th International Conference on Computer Supported Education - Volume 3: CSEDU,},
year={2014},
pages={124-129},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004958601240129},
isbn={978-989-758-022-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Computer Supported Education - Volume 3: CSEDU,
TI - The Impact of High Dropout Rates in a Large Public Brazilian University - A Quantitative Approach Using Educational Data Mining
SN - 978-989-758-022-2
AU - Mary Barbosa Manhães L.
AU - Manuel Serra da Cruz S.
AU - Zimbrão G.
PY - 2014
SP - 124
EP - 129
DO - 10.5220/0004958601240129