Explainability in Intelligent Analysis of Students considering Dropout Factors: some insights
Resumo
Context: In public institutions, there is great concern about the average number of students graduating at the end of undergraduate studies, which substantially impacts public higher education policies and public investments in Brazilian universities. Moreover, dropout imposes a financial and human burden, preventing students from learning. Problem: Brazil witnessed a university dropout rate of almost 55%. This problem affects society in general, which needs more suitably qualified professionals to face the challenges of the job market. Solution: This work aims to analyze, through AI explainability algorithms, the specific factors that lead to student dropout, considering specific courses from the great areas of science. We strive to explore the profile of students who have dropped out in recent years, stratified by course. Explainability algorithms allow the formal inspection of each factor that led to the dropout. Method: We used the Design Science Research methodology to conduct our study. An analysis with data from a specific university, considering the GDPR, was conducted to verify the proposal’s feasibility. Results: Our results show that the solution can help identify key factors that lead to dropping out, stratified by areas, helping to provide specific actions to deal with this problem in universities.Referências
Adachi, A. (2009). Evasion and dropouts from ufmg undergraduate courses. In Portuguese. Pós em Educação - UFMG, Minas Gerais.
Aguirre, C. E. and Pérez, J. C. (2020). Predictive data analysis techniques applied to dropping out of university studies. In 2020 XLVI Latin American Computing Conference (CLEI), pages 512–521. IEEE.
Ajoodha, R., Dukhan, S., and Jadhav, A. (2020). Data-driven student support for academic success by developing student skill profiles. In 2020 2nd International Multidisciplinary Information Technology and Engineering Conference (IMITEC), pages 1–8. IEEE.
Aquines Gutiérrez, O., Hernández Taylor, D. M., Santos-Guevara, A., Chavarría-Garza, W. X., Martínez-Huerta, H., and Galloway, R. K. (2022). How the entry profiles and early study habits are related to first-year academic performance in engineering programs. Sustainability, 14(22):15400.
Assis, M. V. O. and Marcolino, A. S. (2024). A predictive model for dropout risk in a computer science education program. In Simpósio Brasileiro de Informática na Educação (SBIE), 35, pages 1560–1573, Rio de Janeiro/RJ. Sociedade Brasileira de Computação.
Aulck, L. et al. (2019). Mining university registrar records to predict first-year undergraduate attrition. pages 9–18. No publisher listed.
Azy, W., Braga, R., Stroele, V., David, J. M. N., Campos, F., Chaves, L. J., and Campos, L. (2024). Intelligent analysis of students profile about dropout factors: A study in information system course context. In Anais do XXXV Simpósio Brasileiro de Informática na Educação (SBIE), Rio de Janeiro, RJ. Sociedade Brasileira de Computação.
Baranyi, M., Nagy, M., and Molontay, R. (2020). Interpretable deep learning for university dropout prediction. pages 13–19. Cited by: 57.
Bardagi, M. and Hutz, C. (2014). University dropout and student support services: a brief review of brazilian literature. Psicologia Revista. In Portuguese. Accessed: Aug. 2023.
Basili, V. R. and Weiss, D. M. (1984). A methodology for collecting valid software engineering data. IEEE Transactions on Software Engineering, (6):728–738.
Boulic, R. and Renault, O. (1991). 3d hierarchies for animation. In Magnenat-Thalmann, N. and Thalmann, D., editors, New Trends in Animation and Visualization. John Wiley & Sons ltd.
Cunha, A., Tunes, E., and Da Silva, R. (2001). Evasion from the chemistry course at the university of brasília: The interpretation of the evoked student. Química Nova. In Portuguese. Accessed: Aug. 2023.
da Cruz, R. C., Juliano, R. C., Monteiro Souza, F. C., and Correa Souza, A. C. (2023). A score approach to identify the risk of students dropout: an experiment with information systems course. In Proceedings of the XIX Brazilian Symposium on Information Systems, pages 120–127.
da Silva, C. (2021). A holistic profile ontology for undergraduate students. In Portuguese. Accessed: Aug. 2023.
da Silva, L. M., Dias, L. P. S., Rigo, S., Barbosa, J. L. V., Leithardt, D. R., and Leithardt, V. R. Q. (2021). A literature review on intelligent services applied to distance learning. Education Sciences, 11(11):666.
de Oliveira, P., da Silva, G., Dourado, R., and Rodrigues, R. L. (2021). Linking engagement profiles to academic performance through sna and cluster analysis on discussion forum data. In LALA, pages 39–47.
Educação, D. (2022). Evasion breaks records in higher education. In Portuguese. Accessed: Aug. 2023.
El-Rady, A. A. (2020). An ontological model to predict dropout students using machine learning techniques.
Federal, G. General data protection law (lgpd) - brazil. effective date. Available at: [link].
Fernández-López, M., Gómez-Pérez, A., and Juristo, N. (1997). Methontology: from ontological art towards ontological engineering. In Spring Symposium Series. Facultad de Informática (UPM).
Gonzalez-Nucamendi, A., Noguez, J., Neri, L., Robledo-Rella, V., García-Castelán, R. M. G., and Escobar-Castillejos, D. (2022). Learning analytics to determine profile dimensions of students associated with their academic performance. Applied Sciences, 12(20):10560.
Gruber, T. R. (1993). A translation approach to portable ontology specifications.
INEP (2017). Methodology for calculating higher education flow indicators. In Portuguese.
Knuth, D. E. (1984). The TEX Book. Addison-Wesley, 15th edition.
Kochkach, A., Kacem, S. B., Elkosantini, S., Lee, S. M., and Suh, W. (2024). On the different concepts and taxonomies of explainable artificial intelligence. In Bennour, A., Bouridane, A., and Chaari, L., editors, Intelligent Systems and Pattern Recognition. ISPR 2023, volume 1941 of Communications in Computer and Information Science. Springer, Cham.
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 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’15).
Liu, B., Li, C., and Wan, Z. (2025). Using explainable ai (xai) to identify and intervene with students in need: A review. In Proceedings of the 2024 3rd International Conference on Artificial Intelligence and Education (ICAIE ’24), pages 636–641, New York, NY, USA. Association for Computing Machinery.
Menolli, A., Horita, F., Dias, J. J. L., and Coelho, R. (2020). Bi–based methodology for analyzing higher education: A case study of dropout phenomenon in information systems courses. In XVI Brazilian Symposium on Information Systems, pages 1–8.
Mishra, P. (2021). Practical explainable AI using Python: artificial intelligence model explanations using Python-based libraries, extensions, and frameworks. Apress, Berkeley, CA.
Mishra, P. (2022). Practical explainable AI using python: Artificial intelligence model explanations using python-based libraries, extensions, and frameworks. Apress.
Mourão, E. et al. (2020). On the performance of hybrid search strategies for systematic literature reviews in software engineering. Information and Software Technology, 123:106294.
Ozkaya, I. (2023). Application of large language models to software engineering tasks: Opportunities, risks, and implications. IEEE Software, 40(3):4–8.
Peffers, K., Rothenberger, M., Tuunanen, T., and Vaezi, R. (2007). A design science research methodology for information systems research. Journal of Management Information Systems, 24(3):45–77.
Priyambada, S. A., Er, M., Yahya, B. N., and Usagawa, T. (2021). Profile-based cluster evolution analysis: Identification of migration patterns for understanding student learning behavior. IEEE Access, 9:101718–101728.
Ram, S. et al. (2015). Using big data for predicting freshmen retention. No publisher listed.
Runeson, P. and Höst, M. (2009). Guidelines for conducting and reporting case study research in software engineering. Empirical Software Engineering, 14:131–164.
Saito, T. and Rehmsmeier, M. (2015). The precision-recall plot is more informative than the roc plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE, 10(3):e0118432.
Saqr, M., López-Pernas, S., Helske, S., and Hrastinski, S. (2023). The longitudinal association between engagement and achievement varies by time, students’ profiles, and achievement state: A full program study. Computers & Education, 199:104787.
SEMESP (2024a). Mapa do ensino superior, 14ª edição / 2024. Accessed on: 7 Dec. 2024.
SEMESP (2024b). Mapa do ensino superior no brasil. Accessed on: 5 Jun. 2024.
Senthil Kumaran, V. and Malar, B. (2023). Distributed ensemble based iterative classification for churn analysis and prediction of dropout ratio in e-learning. Interactive Learning Environments, 31(7):4235–4250.
Sharma, P. (2023). Utilizing explainable artificial intelligence to address deep learning in biomedical domain. In Medical data analysis and processing using explainable artificial intelligence, pages 19–38. CRC Press.
Shevskaya, N. V. (2021). Explainable artificial intelligence approaches: Challenges and perspectives. In 2021 International Conference on Quality Management, Transport and Information Security, Information Technologies (IT&QM&IS). IEEE.
Silva, F. d. C., Feitosa, R. M., Batista, L. A., and Santana, A. M. (2024). Análise comparativa de métodos de explicabilidade da inteligência artificial no cenário educacional: um estudo de caso sobre evasão. In Simpósio Brasileiro de Informática na Educação (SBIE), 35, pages 2968–2977, Rio de Janeiro/RJ. Sociedade Brasileira de Computação.
Silva, F. d. C., Santana, A. M., and Feitosa, R. M. (2025). An investigation into dropout indicators in secondary technical education using explainable artificial intelligence. IEEE Revista Iberoamericana de Tecnologias del Aprendizaje, 20:105–114.
Smith, A. and Jones, B. (1999). On the complexity of computing. In Smith-Jones, A. B., editor, Advances in Computer Science, pages 555–566. Publishing Press.
Vasanth, S., Keerthana, S., and Saravanan, G. (2024). Demystifying ai: A robust and comprehensive approach to explainable ai. In 2024 International Conference on Intelligent Computing and Emerging Communication Technologies (ICEC), pages 1–5. IEEE.
Veloso, T. and De Almeida, E. (2024). Evasion in ufmt undergraduate courses. 24ª Reunião Anual - Technical Report. In Portuguese.
Vinker, E. and Rubinstein, A. (2022). Mining code submissions to elucidate disengagement in a computer science mooc. In LAK22: 12th International Learning Analytics and Knowledge Conference, pages 142–151.
World Wide Web Consortium (2012). Owl 2 web ontology language document overview. W3C Recommendation.
Aguirre, C. E. and Pérez, J. C. (2020). Predictive data analysis techniques applied to dropping out of university studies. In 2020 XLVI Latin American Computing Conference (CLEI), pages 512–521. IEEE.
Ajoodha, R., Dukhan, S., and Jadhav, A. (2020). Data-driven student support for academic success by developing student skill profiles. In 2020 2nd International Multidisciplinary Information Technology and Engineering Conference (IMITEC), pages 1–8. IEEE.
Aquines Gutiérrez, O., Hernández Taylor, D. M., Santos-Guevara, A., Chavarría-Garza, W. X., Martínez-Huerta, H., and Galloway, R. K. (2022). How the entry profiles and early study habits are related to first-year academic performance in engineering programs. Sustainability, 14(22):15400.
Assis, M. V. O. and Marcolino, A. S. (2024). A predictive model for dropout risk in a computer science education program. In Simpósio Brasileiro de Informática na Educação (SBIE), 35, pages 1560–1573, Rio de Janeiro/RJ. Sociedade Brasileira de Computação.
Aulck, L. et al. (2019). Mining university registrar records to predict first-year undergraduate attrition. pages 9–18. No publisher listed.
Azy, W., Braga, R., Stroele, V., David, J. M. N., Campos, F., Chaves, L. J., and Campos, L. (2024). Intelligent analysis of students profile about dropout factors: A study in information system course context. In Anais do XXXV Simpósio Brasileiro de Informática na Educação (SBIE), Rio de Janeiro, RJ. Sociedade Brasileira de Computação.
Baranyi, M., Nagy, M., and Molontay, R. (2020). Interpretable deep learning for university dropout prediction. pages 13–19. Cited by: 57.
Bardagi, M. and Hutz, C. (2014). University dropout and student support services: a brief review of brazilian literature. Psicologia Revista. In Portuguese. Accessed: Aug. 2023.
Basili, V. R. and Weiss, D. M. (1984). A methodology for collecting valid software engineering data. IEEE Transactions on Software Engineering, (6):728–738.
Boulic, R. and Renault, O. (1991). 3d hierarchies for animation. In Magnenat-Thalmann, N. and Thalmann, D., editors, New Trends in Animation and Visualization. John Wiley & Sons ltd.
Cunha, A., Tunes, E., and Da Silva, R. (2001). Evasion from the chemistry course at the university of brasília: The interpretation of the evoked student. Química Nova. In Portuguese. Accessed: Aug. 2023.
da Cruz, R. C., Juliano, R. C., Monteiro Souza, F. C., and Correa Souza, A. C. (2023). A score approach to identify the risk of students dropout: an experiment with information systems course. In Proceedings of the XIX Brazilian Symposium on Information Systems, pages 120–127.
da Silva, C. (2021). A holistic profile ontology for undergraduate students. In Portuguese. Accessed: Aug. 2023.
da Silva, L. M., Dias, L. P. S., Rigo, S., Barbosa, J. L. V., Leithardt, D. R., and Leithardt, V. R. Q. (2021). A literature review on intelligent services applied to distance learning. Education Sciences, 11(11):666.
de Oliveira, P., da Silva, G., Dourado, R., and Rodrigues, R. L. (2021). Linking engagement profiles to academic performance through sna and cluster analysis on discussion forum data. In LALA, pages 39–47.
Educação, D. (2022). Evasion breaks records in higher education. In Portuguese. Accessed: Aug. 2023.
El-Rady, A. A. (2020). An ontological model to predict dropout students using machine learning techniques.
Federal, G. General data protection law (lgpd) - brazil. effective date. Available at: [link].
Fernández-López, M., Gómez-Pérez, A., and Juristo, N. (1997). Methontology: from ontological art towards ontological engineering. In Spring Symposium Series. Facultad de Informática (UPM).
Gonzalez-Nucamendi, A., Noguez, J., Neri, L., Robledo-Rella, V., García-Castelán, R. M. G., and Escobar-Castillejos, D. (2022). Learning analytics to determine profile dimensions of students associated with their academic performance. Applied Sciences, 12(20):10560.
Gruber, T. R. (1993). A translation approach to portable ontology specifications.
INEP (2017). Methodology for calculating higher education flow indicators. In Portuguese.
Knuth, D. E. (1984). The TEX Book. Addison-Wesley, 15th edition.
Kochkach, A., Kacem, S. B., Elkosantini, S., Lee, S. M., and Suh, W. (2024). On the different concepts and taxonomies of explainable artificial intelligence. In Bennour, A., Bouridane, A., and Chaari, L., editors, Intelligent Systems and Pattern Recognition. ISPR 2023, volume 1941 of Communications in Computer and Information Science. Springer, Cham.
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 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’15).
Liu, B., Li, C., and Wan, Z. (2025). Using explainable ai (xai) to identify and intervene with students in need: A review. In Proceedings of the 2024 3rd International Conference on Artificial Intelligence and Education (ICAIE ’24), pages 636–641, New York, NY, USA. Association for Computing Machinery.
Menolli, A., Horita, F., Dias, J. J. L., and Coelho, R. (2020). Bi–based methodology for analyzing higher education: A case study of dropout phenomenon in information systems courses. In XVI Brazilian Symposium on Information Systems, pages 1–8.
Mishra, P. (2021). Practical explainable AI using Python: artificial intelligence model explanations using Python-based libraries, extensions, and frameworks. Apress, Berkeley, CA.
Mishra, P. (2022). Practical explainable AI using python: Artificial intelligence model explanations using python-based libraries, extensions, and frameworks. Apress.
Mourão, E. et al. (2020). On the performance of hybrid search strategies for systematic literature reviews in software engineering. Information and Software Technology, 123:106294.
Ozkaya, I. (2023). Application of large language models to software engineering tasks: Opportunities, risks, and implications. IEEE Software, 40(3):4–8.
Peffers, K., Rothenberger, M., Tuunanen, T., and Vaezi, R. (2007). A design science research methodology for information systems research. Journal of Management Information Systems, 24(3):45–77.
Priyambada, S. A., Er, M., Yahya, B. N., and Usagawa, T. (2021). Profile-based cluster evolution analysis: Identification of migration patterns for understanding student learning behavior. IEEE Access, 9:101718–101728.
Ram, S. et al. (2015). Using big data for predicting freshmen retention. No publisher listed.
Runeson, P. and Höst, M. (2009). Guidelines for conducting and reporting case study research in software engineering. Empirical Software Engineering, 14:131–164.
Saito, T. and Rehmsmeier, M. (2015). The precision-recall plot is more informative than the roc plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE, 10(3):e0118432.
Saqr, M., López-Pernas, S., Helske, S., and Hrastinski, S. (2023). The longitudinal association between engagement and achievement varies by time, students’ profiles, and achievement state: A full program study. Computers & Education, 199:104787.
SEMESP (2024a). Mapa do ensino superior, 14ª edição / 2024. Accessed on: 7 Dec. 2024.
SEMESP (2024b). Mapa do ensino superior no brasil. Accessed on: 5 Jun. 2024.
Senthil Kumaran, V. and Malar, B. (2023). Distributed ensemble based iterative classification for churn analysis and prediction of dropout ratio in e-learning. Interactive Learning Environments, 31(7):4235–4250.
Sharma, P. (2023). Utilizing explainable artificial intelligence to address deep learning in biomedical domain. In Medical data analysis and processing using explainable artificial intelligence, pages 19–38. CRC Press.
Shevskaya, N. V. (2021). Explainable artificial intelligence approaches: Challenges and perspectives. In 2021 International Conference on Quality Management, Transport and Information Security, Information Technologies (IT&QM&IS). IEEE.
Silva, F. d. C., Feitosa, R. M., Batista, L. A., and Santana, A. M. (2024). Análise comparativa de métodos de explicabilidade da inteligência artificial no cenário educacional: um estudo de caso sobre evasão. In Simpósio Brasileiro de Informática na Educação (SBIE), 35, pages 2968–2977, Rio de Janeiro/RJ. Sociedade Brasileira de Computação.
Silva, F. d. C., Santana, A. M., and Feitosa, R. M. (2025). An investigation into dropout indicators in secondary technical education using explainable artificial intelligence. IEEE Revista Iberoamericana de Tecnologias del Aprendizaje, 20:105–114.
Smith, A. and Jones, B. (1999). On the complexity of computing. In Smith-Jones, A. B., editor, Advances in Computer Science, pages 555–566. Publishing Press.
Vasanth, S., Keerthana, S., and Saravanan, G. (2024). Demystifying ai: A robust and comprehensive approach to explainable ai. In 2024 International Conference on Intelligent Computing and Emerging Communication Technologies (ICEC), pages 1–5. IEEE.
Veloso, T. and De Almeida, E. (2024). Evasion in ufmt undergraduate courses. 24ª Reunião Anual - Technical Report. In Portuguese.
Vinker, E. and Rubinstein, A. (2022). Mining code submissions to elucidate disengagement in a computer science mooc. In LAK22: 12th International Learning Analytics and Knowledge Conference, pages 142–151.
World Wide Web Consortium (2012). Owl 2 web ontology language document overview. W3C Recommendation.
Publicado
24/11/2025
Como Citar
AZY, Wallyce; BRAGA, Regina; STROELE, Victor; DAVID, José Maria; CAMPOS, Fernanda.
Explainability in Intelligent Analysis of Students considering Dropout Factors: some insights. In: SIMPÓSIO BRASILEIRO DE INFORMÁTICA NA EDUCAÇÃO (SBIE), 36. , 2025, Curitiba/PR.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 857-872.
DOI: https://doi.org/10.5753/sbie.2025.12698.
