Quando o Risco Acadêmico se Torna Visível? O Papel da Persistência Temporal
Resumo
O monitoramento precoce de estudantes em risco de resultados acadêmicos adversos é essencial para a realização de intervenções educacionais eficazes. Neste artigo, investigamos a dinâmica temporal do risco acadêmico utilizando dados longitudinais do ensino médio brasileiro. Analisamos trajetórias mensais de risco geradas por abordagens de predição em nível nacional e estadual e caracterizamos os estudantes de acordo com perfis temporais de risco. A regressão logística de efeitos mistos mostrou que perfis persistentes aumentam em mais de três vezes as chances de continuidade futura do risco em comparação com estudantes recentemente sinalizados (OR > 3.3). Esses resultados sugerem que a visibilidade do risco acadêmico não é determinada apenas pela presença de um sinal de alerta, mas também por sua persistência ao longo do tempo, fornecendo informações adicionais para a priorização de intervenções educacionais.
Palavras-chave:
Risco Acadêmico, Persistência Temporal, Sistemas de Alerta Precoce
Referências
Balaji, P., Alelyani, S., Qahmash, A., and Mohana, M. (2021). Contributions of machine learning models towards student academic performance prediction: a systematic review. Applied Sciences, 11(21):10007.
Barros, A. N., Queiroga, E. M., Marcolino, M. R., Silva, D. B. L., Dermeval, D., Lima, A., Marques, L. B., Cechinel, C., and Vieira, T. (2025). Ensuring data quality in national educational databases: Insights from brazil's centralized database of high school students' data. In Conference on Digital Government Research, volume 1.
Barros, A. N., Roque, F. V., Paulino, T., Schmidt, A., Galvani, F., Oliveira, R., Marques, L. B., Dermeval, D., Stefani, A. G. M., Costa, M. D. S. D., Queiroga, E. M., Oliveira, E., Cechinel, C., and Vieira, T. (2026). Interpretable machine learning for predicting school absenteeism at-scale in Brazil: evidence from 22,000 schools. Scientific Reports.
Breslow, N. E. and Clayton, D. G. (1993). Approximate inference in generalized linear mixed models. Journal of the American statistical Association, 88(421):9–25.
Cechinel, C., Arantes, F., Pessoa, M., Santana, D. S., Madeira, R. d. A., Cunha, S. F. d., de Oliveira, A. B., Roque, F., Freires, L., de Aguiar, M. A., Vieira, T., Bittencourt, I. I., Isotani, S., and Queiroga, E. M. (2026). The sews framework: Bridging the prediction-to-action gap in educational early warning systems. In Blanchard, E. G., Chen, G., Chi, M., and Isotani, S., editors, Artificial Intelligence in Education. Late Breaking Results, WideAIED, Practitioners, Industry and Policies, Blue Sky, Doctoral Consortium, FoL Workshops and Tutorials, FoL Invited Papers, pages 442–456, Cham. Springer Nature Switzerland.
Christie, S. T., Shi, A., Gobert, L., and Rosen, C. (2019). Machine-learned school dropout early warning at scale. In Proceedings of the 12th International Conference on Educational Data Mining.
Coleman, C., Baker, T., and Stephenson, E. (2019). A better cold-start for early prediction of student at-risk status in new school districts. In Proceedings of the 12th International Conference on Educational Data Mining.
Cramér, H. (1999). Mathematical methods of statistics, volume 9. Princeton university press.
Ferguson, R. (2012). Learning analytics: drivers, developments and challenges. International Journal of Technology Enhanced Learning, 4(5/6):304–317.
Francisco, T. V., Barros, A. N., Roque, F. V., Paulino, T., Schmidt, A., Galvani, F., Oliveira, R., Marques, L. B., Dermeval, D., Barreto, P., Stefani, A. G. M., de Santana da Costa, M., Queiroga, E. M., Oliveira, E., Bittencourt, I. I., Cechinel, C., and Vieira, T. (2027). Territorial fairness in large-scale academic risk prediction: Comparing national and state-level machine learning models in brazil. In Blanchard, E. G., Chen, G., Chi, M., and Isotani, S., editors, Artificial Intelligence in Education, pages 225–239, Cham. Springer Nature Switzerland.
Holm, S. (1979). A simple sequentially rejective multiple test procedure. Scandinavian journal of statistics, pages 65–70.
Howard, E., Meehan, M., and Parnell, A. (2018). Contrasting prediction methods for early warning systems at undergraduate level. The Internet and Higher Education, 37:66–75.
Lakkaraju, H., Aguiar, E., Shan, C., Miller, D., Bhanpuri, N., Ghani, R., and Addison, K. L. (2015). A machine learning framework to identify students at risk of adverse academic outcomes. In Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 1909–1918.
Lee, S. and Chung, J. Y. (2019). The machine learning-based dropout early warning system for improving the performance of dropout prediction. Applied Sciences, 9(15):3093.
McHugh, M. L. (2013). The chi-square test of independence. Biochemia medica, 23(2):143–149.
Mosia, M. (2025). A bayesian state-space approach to dynamic hierarchical logistic regression for evolving student risk in educational analytics. Data, 10(2):23.
Parr, A. K. and Bonitz, V. S. (2015). Role of family background, student behaviors, and school-related beliefs in predicting high school dropout. The Journal of Educational Research, 108(6):504–514.
Queiroga, E. M., Paragarino, V. R., Casas, A. P., Primo, T. T., Munoz, R., Ramos, V. C., and Cechinel, C. (2022). Early prediction of at-risk students in secondary education: A countrywide k-12 learning analytics initiative in uruguay. Information, 13(9):401.
Queiroga, E. M., Santana, D., da Silva, M., de Aguiar, M., dos Santos, V., Mello, R. F., Bittencourt, I. I., and Cechinel, C. (2024a). Anticipating student abandonment and failure: Predictive models in high school settings. In International Conference on Artificial Intelligence in Education, pages 351–364. Springer.
Queiroga, E. M., Siqueira, E. S., Portela, C. D. S., Cordeiro, T. D., Bittencourt, I. I., Isotani, S., Mello, R. F., Muñoz, R., and Cechinel, C. (2024b). Data-driven strategies for achieving school equity: Insights from brazil and policy recommendations. IEEE Access, 12:101646–101659.
Romero, C. and Ventura, S. (2020). Educational data mining and learning analytics: An updated survey. WIREs Data Mining and Knowledge Discovery, 10(3):e1355.
Sara, N.-B., Halland, R., Igel, I. G., and Alstrup, S. (2015). High-school dropout prediction using machine learning: A danish large-scale study. In Proceedings of the 23rd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning.
UIS - UNESCO Institute for Statistics (2012). Global education digest 2012—opportunities lost: The impact of grade repetition and early school leaving.
Barros, A. N., Queiroga, E. M., Marcolino, M. R., Silva, D. B. L., Dermeval, D., Lima, A., Marques, L. B., Cechinel, C., and Vieira, T. (2025). Ensuring data quality in national educational databases: Insights from brazil's centralized database of high school students' data. In Conference on Digital Government Research, volume 1.
Barros, A. N., Roque, F. V., Paulino, T., Schmidt, A., Galvani, F., Oliveira, R., Marques, L. B., Dermeval, D., Stefani, A. G. M., Costa, M. D. S. D., Queiroga, E. M., Oliveira, E., Cechinel, C., and Vieira, T. (2026). Interpretable machine learning for predicting school absenteeism at-scale in Brazil: evidence from 22,000 schools. Scientific Reports.
Breslow, N. E. and Clayton, D. G. (1993). Approximate inference in generalized linear mixed models. Journal of the American statistical Association, 88(421):9–25.
Cechinel, C., Arantes, F., Pessoa, M., Santana, D. S., Madeira, R. d. A., Cunha, S. F. d., de Oliveira, A. B., Roque, F., Freires, L., de Aguiar, M. A., Vieira, T., Bittencourt, I. I., Isotani, S., and Queiroga, E. M. (2026). The sews framework: Bridging the prediction-to-action gap in educational early warning systems. In Blanchard, E. G., Chen, G., Chi, M., and Isotani, S., editors, Artificial Intelligence in Education. Late Breaking Results, WideAIED, Practitioners, Industry and Policies, Blue Sky, Doctoral Consortium, FoL Workshops and Tutorials, FoL Invited Papers, pages 442–456, Cham. Springer Nature Switzerland.
Christie, S. T., Shi, A., Gobert, L., and Rosen, C. (2019). Machine-learned school dropout early warning at scale. In Proceedings of the 12th International Conference on Educational Data Mining.
Coleman, C., Baker, T., and Stephenson, E. (2019). A better cold-start for early prediction of student at-risk status in new school districts. In Proceedings of the 12th International Conference on Educational Data Mining.
Cramér, H. (1999). Mathematical methods of statistics, volume 9. Princeton university press.
Ferguson, R. (2012). Learning analytics: drivers, developments and challenges. International Journal of Technology Enhanced Learning, 4(5/6):304–317.
Francisco, T. V., Barros, A. N., Roque, F. V., Paulino, T., Schmidt, A., Galvani, F., Oliveira, R., Marques, L. B., Dermeval, D., Barreto, P., Stefani, A. G. M., de Santana da Costa, M., Queiroga, E. M., Oliveira, E., Bittencourt, I. I., Cechinel, C., and Vieira, T. (2027). Territorial fairness in large-scale academic risk prediction: Comparing national and state-level machine learning models in brazil. In Blanchard, E. G., Chen, G., Chi, M., and Isotani, S., editors, Artificial Intelligence in Education, pages 225–239, Cham. Springer Nature Switzerland.
Holm, S. (1979). A simple sequentially rejective multiple test procedure. Scandinavian journal of statistics, pages 65–70.
Howard, E., Meehan, M., and Parnell, A. (2018). Contrasting prediction methods for early warning systems at undergraduate level. The Internet and Higher Education, 37:66–75.
Lakkaraju, H., Aguiar, E., Shan, C., Miller, D., Bhanpuri, N., Ghani, R., and Addison, K. L. (2015). A machine learning framework to identify students at risk of adverse academic outcomes. In Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 1909–1918.
Lee, S. and Chung, J. Y. (2019). The machine learning-based dropout early warning system for improving the performance of dropout prediction. Applied Sciences, 9(15):3093.
McHugh, M. L. (2013). The chi-square test of independence. Biochemia medica, 23(2):143–149.
Mosia, M. (2025). A bayesian state-space approach to dynamic hierarchical logistic regression for evolving student risk in educational analytics. Data, 10(2):23.
Parr, A. K. and Bonitz, V. S. (2015). Role of family background, student behaviors, and school-related beliefs in predicting high school dropout. The Journal of Educational Research, 108(6):504–514.
Queiroga, E. M., Paragarino, V. R., Casas, A. P., Primo, T. T., Munoz, R., Ramos, V. C., and Cechinel, C. (2022). Early prediction of at-risk students in secondary education: A countrywide k-12 learning analytics initiative in uruguay. Information, 13(9):401.
Queiroga, E. M., Santana, D., da Silva, M., de Aguiar, M., dos Santos, V., Mello, R. F., Bittencourt, I. I., and Cechinel, C. (2024a). Anticipating student abandonment and failure: Predictive models in high school settings. In International Conference on Artificial Intelligence in Education, pages 351–364. Springer.
Queiroga, E. M., Siqueira, E. S., Portela, C. D. S., Cordeiro, T. D., Bittencourt, I. I., Isotani, S., Mello, R. F., Muñoz, R., and Cechinel, C. (2024b). Data-driven strategies for achieving school equity: Insights from brazil and policy recommendations. IEEE Access, 12:101646–101659.
Romero, C. and Ventura, S. (2020). Educational data mining and learning analytics: An updated survey. WIREs Data Mining and Knowledge Discovery, 10(3):e1355.
Sara, N.-B., Halland, R., Igel, I. G., and Alstrup, S. (2015). High-school dropout prediction using machine learning: A danish large-scale study. In Proceedings of the 23rd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning.
UIS - UNESCO Institute for Statistics (2012). Global education digest 2012—opportunities lost: The impact of grade repetition and early school leaving.
Publicado
05/10/2026
Como Citar
FRANCISCO, Tobias Vieira et al.
Quando o Risco Acadêmico se Torna Visível? O Papel da Persistência Temporal. In: SIMPÓSIO BRASILEIRO DE INFORMÁTICA NA EDUCAÇÃO (SBIE), 37. , 2026, Goiânia/GO.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 745-760.
DOI: https://doi.org/10.5753/sbie.2026.27293.
