An Early Warning Model for School Dropout: a Case Study in E-learning Class

• Felipe Neves Universidade Federal de Juiz de Fora (UFJF)
• Fernanda Campos Universidade Federal de Juiz de Fora (UFJF)
• Victor Ströele Universidade Federal de Juiz de Fora (UFJF)
• Mário Dantas Universidade Federal de Juiz de Fora (UFJF)

DOI: https://doi.org/10.5753/cbie.sbie.2019.1441

Resumo

Dropping out of school is a real challenge for educational specialists. Considering distance education classes, we have to deal with a huge number of students' disengagement with social and economic consequences. In order to solve the early dropout problem, this paper proposes the use of an Early Warning System capable of predicting the disengagement of students along the class and notify teachers about this behavior, enabling them to intervene in an effective way and make student's success possible. In order to evaluate our proposal, we carried out a case study which showed the feasibility of the proposal and the use of its technologies. The results pointed out a significant increase of gain in accuracy along the course, reaching 93% of precision at the end.

Palavras-chave: School Dropout, Distance Education, Early Warning System, Machine Learning

Referências

Bagheri, M. and Movahed, S. H. (2016). The effect of the internet of things (iot) on education business model. In 2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), pages 435–441. IEEE.

Barbosa, A., Santos, E., and Pordeus, J. P. (2017). A machine learning approach to identify and prioritize college students at risk of dropping out. In Brazilian Symposium on Computers in Education (Simpósio Brasileiro de Informática na Educação - SBIE), volume 28, page 1497.

Breiman, L. (2001). Random forests. Machine learning, 45(1):5–32.

Cerezo, R., Bogarín, A., Esteban, M., and Romero, C. (2019). Process mining for self-regulated learning assessment in e-learning. Journal of Computing in Higher Education, pages 1–15.

Denil, M., Shakibi, B., Dinh, L., De Freitas, N., et al. (2013). Predicting parameters in deep learning. In Advances in neural information processing systems, pages 2148–2156.

Grasso, V. F. and Singh, A. (2011). Early warning systems: State-of-art analysis and future directions. Draft report, UNEP, 1.

Hamers, B., Suykens, J., Leemans, V., and De Moor, B. (2003). Ensemble learning of coupled parameterized kernel models. In Supplementary Proc. of the International Conference on Artificial Neural Networks and International Conference on Neural Information Processing (ICANN/ICONIP), pages 130–133.

Han, J., Pei, J., and Kamber, M. (2011). Data mining: concepts and techniques. Elsevier.

Kumari, P., Jain, P. K., and Pamula, R. (2018). An efficient use of ensemble methods to predict students' academic performance. In 2018 4th International Conference on Recent Advances in Information Technology (RAIT), pages 1–6. IEEE.

Márquez-Vera, C., Cano, A., Romero, C., Noaman, A. Y. M., Mousa Fardoun, H., and Ventura, S. (2016). Early dropout prediction using data mining: a case study with high school students. Expert Systems, 33(1):107–124.

Neves, F., Ströele, V., and Campos, F. (2019). Information diffusion in social networks: a recommendation model in the educational context. In Proceedings of the XV Brazilian Symposium on Information Systems, page 25. ACM.

Pereira, C. K., Campos, F., Ströele, V., David, J. M. N., and Braga, R. (2018). Broad-rsi - educational recommender system using social networks interactions and linked data. Journal of Internet Services and Applications, 9(1):7.

Runeson, P., Host, M., Rainer, A., and Regnell, B. (2012). Case study research in software engineering: Guidelines and examples. John Wiley & Sons.

Sokolova, M. and Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4):427–437.

Wohlin, C., Runeson, P., Höst, M., Ohlsson, M. C., Regnell, B., and Wesslén, A. (2012). Experimentation in software engineering. Springer Science & Business Media.