A Predictive Model for Dropout Risk in a Computer Science Education Program
Resumo
The ever-growing demand for computing professionals requires the effective management of educational resources. With the increasing importance of computer science education programs in Brazil, identifying potential dropout students has become crucial for educational institutions. However, predicting which students are likely to drop out poses a significant challenge, especially in non-metropolitan areas. To address this issue in the Computer Science Education program of the Federal University of Paraná (Brazil), we propose an approach that leverages machine learning to analyze different features associated with the student's academic performance and detect possible dropouts. We compare the performance of 15 machine learning algorithms in predicting student dropouts, additionally identifying the most influential variables contributing to this situation. To evaluate the effectiveness of our approach, we conduct experiments using real data collected from the computer science education program. The results demonstrate the efficacy of our approach in identifying students at risk of dropping out.
Palavras-chave:
IA na Educação, Previsão de Evasão de Alunos, Aprendizagem de Máquina, Licenciatura em Computação
Referências
Ali, M. (2020). PyCaret: An open source, low-code machine learning library in Python. PyCaret version 3.0.
Barbosa-Camargo, M. I., García-Sánchez, A., and Ridao-Carlini, M. L. (2021). Inequality and dropout in higher education in colombia. a multilevel analysis of regional differences, institutions, and field of study. Mathematics, 9(24).
BRASIL (2022). Parecer cne/ceb n. 2/2022: Normas sobre computação na educação básica - complemento à base nacional comum curricular (bncc) (only in portuguese). Technical report. Available [link]. Accessed: 09 Oct. 2023.
Bravo, D., Alves, M. Z., Ensina, L., and de Oliveira, L. (2023). Evaluating strategies to predict student dropout of a bachelor's degree in computer science. In Anais do XI Symposium on Knowledge Discovery, Mining and Learning, pages 1–8, Porto Alegre, RS, Brasil. SBC.
Colpo, M., Primo, T., and Aguiar, M. (2021). Predição da evasão estudantil: uma análise comparativa de diferentes representações de treino na aprendizagem de modelos genéricos. In Anais do XXXII Simpósio Brasileiro de Informática na Educação, pages 873–884, Porto Alegre, RS, Brasil. SBC.
de Almeida, C. C. and Mateus, N. M. A. (2015). Licenciandos em computação: experiências formativas proporcionadas pelo pibid e a busca pelo reconhecimento profissional. Horizontes, 33(1).
Del Bonifro, F., Gabbrielli, M., Lisanti, G., and Zingaro, S. P. (2020). Student dropout prediction. In Bittencourt, I. I., Cukurova, M., Muldner, K., Luckin, R., and Millán, E., editors, Artificial Intelligence in Education, pages 129–140, Cham. Springer.
Fluminense, U. F. (2015). Forplad - indicadores. In Fórum de Pró-Reitores de Planejamento e Administração Comissão de Planejamento e Avaliação. Available [link].
Lewine, R., Manley, K., Bailey, G., Warnecke, A., Davis, D., and Sommers, A. (2021). College success among students from disadvantaged backgrounds: “poor” and “rural” do not spell failure. Journal of College Student Retention: Research, Theory and Practice, 23(3):686–698.
Linhares, A. C. O. and Santos, K. S. (2021). A licenciatura em computação no brasil: histórica e contexto atual. Revista Brasileira de Informática na Educação, 29:188–208.
Mathews de, N. S. L., Fachini Gomes, J. B., Holanda, M., Koike, C. C., and Leao Costa, M. T. (2023). Study on computer science undergraduate students dropout at the university of brasilia. In 2023 IEEE Frontiers in Education Conference (FIE), pages 1–7.
Moscoviz, L., Evans, D. K., et al. (2022). Learning loss and student dropouts during the covid-19 pandemic: A review of the evidence two years after schools shut down. Center for Global Development Washington, DC, USA.
Nagy, M. and Molontay, R. (2023). Interpretable dropout prediction: Towards xai-based personalized intervention. Int. J. of Artificial Intelligence in Educ., pages 1–27.
Nascimento, P. A. M. M. and Verhine, R. E. (2017). Considerações sobre o investimento público em educação superior no brasil. Available [link]. Accessed: 08 Mar. 2024.
Olmedo-Cifuentes, I. and Martínez-León, I. M. (2022). University dropout intention: Analysis during covid-19. Journal of Management and Business Education, 5(2).
Santos, G., Belloze, K. T., Tarrataca, L., Haddad, D. B., Bordignon, A. L., and Brandão, D. N. (2020). Evolvedtree: Analyzing student dropout in universities. In 2020 Int. Conf. on Systems, Signals and Image Processing (IWSSIP), pages 173–178. IEEE.
Santos, J., Sousa, J. D., Mello, R., Cristino, C., and Alves, G. (2021). Um modelo para análise do impacto da retenção e evasão no ensino superior utilizando cadeias de markov absorventes. In Anais do XXXII Simpósio Brasileiro de Informática na Educação, pages 813–823, Porto Alegre, RS, Brasil. SBC.
Schefer-Wenzl, S., Miladinovic, I., Bachinger-Raithofer, S., and Muckenhumer, C. (2024). A study on reasons for student dropouts in a computer science bachelor’s degree program. In Auer, M. E., Cukierman, U. R., Vendrell Vidal, E., and Tovar Caro, E., editors, Towards a Hybrid, Flexible and Socially Engaged Higher Education, pages 391–400, Cham. Springer Nature Switzerland.
Tenpipat, W. and Akkarajitsakul, K. (2020). Student dropout prediction: A kmutt case study. In 2020 1st Int. Conf. on Big Data Analytics and Practices, pages 1–5.
Varga, E. B. and Ádám Sátán (2021). Detecting at-risk students on computer science bachelor programs based on pre-enrollment characteristics. Hungarian Educational Research Journal, 11(3):297 – 310.
Viloria, A., Naveda, A. S., Palma, H. H., Núñez, W. N., and Núñez, L. N. (2020). Using big data to determine potential dropouts in higher education. Journal of Physics.
Wegner, R. C. (2022). Evasão no ensino superior: Digressões motivadas a partir da pandemia do novo coronavírus. Revista Docência e Cibercultura, 6(1):01–22.
Barbosa-Camargo, M. I., García-Sánchez, A., and Ridao-Carlini, M. L. (2021). Inequality and dropout in higher education in colombia. a multilevel analysis of regional differences, institutions, and field of study. Mathematics, 9(24).
BRASIL (2022). Parecer cne/ceb n. 2/2022: Normas sobre computação na educação básica - complemento à base nacional comum curricular (bncc) (only in portuguese). Technical report. Available [link]. Accessed: 09 Oct. 2023.
Bravo, D., Alves, M. Z., Ensina, L., and de Oliveira, L. (2023). Evaluating strategies to predict student dropout of a bachelor's degree in computer science. In Anais do XI Symposium on Knowledge Discovery, Mining and Learning, pages 1–8, Porto Alegre, RS, Brasil. SBC.
Colpo, M., Primo, T., and Aguiar, M. (2021). Predição da evasão estudantil: uma análise comparativa de diferentes representações de treino na aprendizagem de modelos genéricos. In Anais do XXXII Simpósio Brasileiro de Informática na Educação, pages 873–884, Porto Alegre, RS, Brasil. SBC.
de Almeida, C. C. and Mateus, N. M. A. (2015). Licenciandos em computação: experiências formativas proporcionadas pelo pibid e a busca pelo reconhecimento profissional. Horizontes, 33(1).
Del Bonifro, F., Gabbrielli, M., Lisanti, G., and Zingaro, S. P. (2020). Student dropout prediction. In Bittencourt, I. I., Cukurova, M., Muldner, K., Luckin, R., and Millán, E., editors, Artificial Intelligence in Education, pages 129–140, Cham. Springer.
Fluminense, U. F. (2015). Forplad - indicadores. In Fórum de Pró-Reitores de Planejamento e Administração Comissão de Planejamento e Avaliação. Available [link].
Lewine, R., Manley, K., Bailey, G., Warnecke, A., Davis, D., and Sommers, A. (2021). College success among students from disadvantaged backgrounds: “poor” and “rural” do not spell failure. Journal of College Student Retention: Research, Theory and Practice, 23(3):686–698.
Linhares, A. C. O. and Santos, K. S. (2021). A licenciatura em computação no brasil: histórica e contexto atual. Revista Brasileira de Informática na Educação, 29:188–208.
Mathews de, N. S. L., Fachini Gomes, J. B., Holanda, M., Koike, C. C., and Leao Costa, M. T. (2023). Study on computer science undergraduate students dropout at the university of brasilia. In 2023 IEEE Frontiers in Education Conference (FIE), pages 1–7.
Moscoviz, L., Evans, D. K., et al. (2022). Learning loss and student dropouts during the covid-19 pandemic: A review of the evidence two years after schools shut down. Center for Global Development Washington, DC, USA.
Nagy, M. and Molontay, R. (2023). Interpretable dropout prediction: Towards xai-based personalized intervention. Int. J. of Artificial Intelligence in Educ., pages 1–27.
Nascimento, P. A. M. M. and Verhine, R. E. (2017). Considerações sobre o investimento público em educação superior no brasil. Available [link]. Accessed: 08 Mar. 2024.
Olmedo-Cifuentes, I. and Martínez-León, I. M. (2022). University dropout intention: Analysis during covid-19. Journal of Management and Business Education, 5(2).
Santos, G., Belloze, K. T., Tarrataca, L., Haddad, D. B., Bordignon, A. L., and Brandão, D. N. (2020). Evolvedtree: Analyzing student dropout in universities. In 2020 Int. Conf. on Systems, Signals and Image Processing (IWSSIP), pages 173–178. IEEE.
Santos, J., Sousa, J. D., Mello, R., Cristino, C., and Alves, G. (2021). Um modelo para análise do impacto da retenção e evasão no ensino superior utilizando cadeias de markov absorventes. In Anais do XXXII Simpósio Brasileiro de Informática na Educação, pages 813–823, Porto Alegre, RS, Brasil. SBC.
Schefer-Wenzl, S., Miladinovic, I., Bachinger-Raithofer, S., and Muckenhumer, C. (2024). A study on reasons for student dropouts in a computer science bachelor’s degree program. In Auer, M. E., Cukierman, U. R., Vendrell Vidal, E., and Tovar Caro, E., editors, Towards a Hybrid, Flexible and Socially Engaged Higher Education, pages 391–400, Cham. Springer Nature Switzerland.
Tenpipat, W. and Akkarajitsakul, K. (2020). Student dropout prediction: A kmutt case study. In 2020 1st Int. Conf. on Big Data Analytics and Practices, pages 1–5.
Varga, E. B. and Ádám Sátán (2021). Detecting at-risk students on computer science bachelor programs based on pre-enrollment characteristics. Hungarian Educational Research Journal, 11(3):297 – 310.
Viloria, A., Naveda, A. S., Palma, H. H., Núñez, W. N., and Núñez, L. N. (2020). Using big data to determine potential dropouts in higher education. Journal of Physics.
Wegner, R. C. (2022). Evasão no ensino superior: Digressões motivadas a partir da pandemia do novo coronavírus. Revista Docência e Cibercultura, 6(1):01–22.
Publicado
04/11/2024
Como Citar
ASSIS, Marcos V. O.; MARCOLINO, Anderson S..
A Predictive Model for Dropout Risk in a Computer Science Education Program. In: SIMPÓSIO BRASILEIRO DE INFORMÁTICA NA EDUCAÇÃO (SBIE), 35. , 2024, Rio de Janeiro/RJ.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 1560-1573.
DOI: https://doi.org/10.5753/sbie.2024.242106.
