Uma Abordagem Baseada em Grafos e Aprendizado de Máquina para Recomendação Curricular em Engenharia
Resumo
Cursos de Engenharia apresentam estruturas complexas de pré-requisitos, fenômenos de retenção e padrões heterogêneos de matrícula, tornando o planejamento acadêmico uma tarefa desafiadora. Este trabalho investiga a integração entre grafos curriculares, grafos de fluxo discente e redes Long Short-Term Memory (LSTM) para apoiar recomendação acadêmica personalizada. Utilizando históricos acadêmicos reais de uma universidade pública brasileira, a abordagem proposta combina informações estruturais, comportamentais e temporais para modelar a progressão estudantil e gerar recomendações curriculares personalizadas baseadas em trajetórias reais de aprendizagem. Os resultados demonstram que o modelo híbrido proposto supera abordagens tradicionais de recomendação, evidenciando sua eficácia para apoiar a progressão acadêmica.
Palavras-chave:
Recomendação Curricular, Grafos Acadêmicos, Redes LSTM
Referências
Burke, R. (2002). Hybrid recommender systems: Survey and experiments. User Modeling and User-Adapted Interaction, 12(4):331–370.
Elbadrawy, A. and Karypis, G. (2016). Domain-aware grade prediction and top-n course recommendation. In RecSys.
Gonçalves, G. S., Serra, F. A. R., Storopoli, J. E., Scafuto, I. C., and Rafael, D. N. (2024). Undergraduate student retention activities: Challenges and research agenda. SAGE Open, 14(3).
Hamilton, W. L. (2020). Graph Representation Learning. Morgan & Claypool.
Heileman, G. L. et al. (2017). Curricular analytics: A framework for reducing time to degree. Computers & Education, 115:18–29.
Hidasi, B. et al. (2016). Session-based recommendations with recurrent neural networks. In ICLR.
Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8):1735–1780.
Instituto Nacional de Estudos e Pesquisas Educacionais Anísio Teixeira (2026). Resumo técnico do censo da educação superior 2024. Technical report, INEP, Brasília, DF.
Lang, C., Siemens, G., Wise, A., and Gašević, D. (2017). Handbook of learning analytics. Society for Learning Analytics Research.
Lorenzo-Quiles, O., Galdón-López, S., and Lendínez-Turón, A. (2023). Factors contributing to university dropout: A review. Frontiers in Education, 8:1159864.
Matcha, W., Gašević, D., Jovanović, J., Uzir, N. A., Oliver, C. W., Murray, A., and Gasevic, D. (2020). Analytics of learning strategies: The association with the personality traits. In Proceedings of the Tenth International Conference on Learning Analytics & Knowledge, pages 151–160. ACM.
McCoy, L., Shapiro, C., and Heileman, G. (2023). Curriculum complexity and student success in higher education: A systematic review. Educational Research Review, 39:100521.
Ministério da Educação (2020). Indicadores da educação superior. [link].
Montagud, M. et al. (2020). Graph-based analysis of curriculum structures. Education Sciences, 10(8):205.
Morsy, S. and Karypis, G. (2019). Cnr: Course recommendation using deep learning. IEEE Access, 7:2019.
Nguyen, A., Gardner, L., and Sheridan, D. (2020). A review of student recommendation systems in higher education. Artificial Intelligence Review, 54(2):1327–1364.
Norris, J. R. (1998). Markov Chains. Cambridge University Press.
Pandey, S. and Karypis, G. (2019). A self-attentive model for knowledge tracing. In IEEE International Conference on Data Mining (ICDM).
Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L., and Sohl-Dickstein, J. (2015a). Deep knowledge tracing. In Advances in Neural Information Processing Systems (NeurIPS), volume 28.
Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L., and Sohl-Dickstein, J. (2015b). Deep knowledge tracing. In Advances in Neural Information Processing Systems (NeurIPS), pages 505–513.
Quadrana, M. et al. (2018). Sequence-aware recommender systems. ACM Computing Surveys, 51(4):1–36.
Ricci, F., Rokach, L., and Shapira, B. (2015). Recommender Systems Handbook. Springer.
Romero, C. and Ventura, S. (2010). Educational data mining: A review of the state of the art. IEEE Transactions on Systems, Man, and Cybernetics, 40(6):601–618.
Salehi, M. and Haghighi, I. N. K. (2013). A course recommender system based on graduated students' experiences. In Proceedings of the 5th Conference on Information and Knowledge Technology (IKT), pages 139–144. IEEE.
Shen, J. et al. (2018). Inferring prerequisite structures from student data. IEEE Transactions on Learning Technologies, 11(2):195–208.
Siemens, G. (2013). Learning analytics: The emergence of a discipline. American Behavioral Scientist, 57(10):1380–1400.
Slim, A. et al. (2014). Curriculum bottlenecks and student progression. In EDM.
Tang, J. and Wang, K. (2018). Personalized top-n sequential recommendation via convolutional sequence embedding. In WSDM.
Viberg, O. et al. (2018). Current trends and issues in learning analytics. Computers in Human Behavior, 89:98–110.
Wu, Q. et al. (2021). Graph neural networks in recommender systems: A survey. ACM Computing Surveys, 55(5):1–37.
Ying, R. et al. (2018). Graph convolutional neural networks for web-scale recommender systems. In KDD.
Elbadrawy, A. and Karypis, G. (2016). Domain-aware grade prediction and top-n course recommendation. In RecSys.
Gonçalves, G. S., Serra, F. A. R., Storopoli, J. E., Scafuto, I. C., and Rafael, D. N. (2024). Undergraduate student retention activities: Challenges and research agenda. SAGE Open, 14(3).
Hamilton, W. L. (2020). Graph Representation Learning. Morgan & Claypool.
Heileman, G. L. et al. (2017). Curricular analytics: A framework for reducing time to degree. Computers & Education, 115:18–29.
Hidasi, B. et al. (2016). Session-based recommendations with recurrent neural networks. In ICLR.
Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8):1735–1780.
Instituto Nacional de Estudos e Pesquisas Educacionais Anísio Teixeira (2026). Resumo técnico do censo da educação superior 2024. Technical report, INEP, Brasília, DF.
Lang, C., Siemens, G., Wise, A., and Gašević, D. (2017). Handbook of learning analytics. Society for Learning Analytics Research.
Lorenzo-Quiles, O., Galdón-López, S., and Lendínez-Turón, A. (2023). Factors contributing to university dropout: A review. Frontiers in Education, 8:1159864.
Matcha, W., Gašević, D., Jovanović, J., Uzir, N. A., Oliver, C. W., Murray, A., and Gasevic, D. (2020). Analytics of learning strategies: The association with the personality traits. In Proceedings of the Tenth International Conference on Learning Analytics & Knowledge, pages 151–160. ACM.
McCoy, L., Shapiro, C., and Heileman, G. (2023). Curriculum complexity and student success in higher education: A systematic review. Educational Research Review, 39:100521.
Ministério da Educação (2020). Indicadores da educação superior. [link].
Montagud, M. et al. (2020). Graph-based analysis of curriculum structures. Education Sciences, 10(8):205.
Morsy, S. and Karypis, G. (2019). Cnr: Course recommendation using deep learning. IEEE Access, 7:2019.
Nguyen, A., Gardner, L., and Sheridan, D. (2020). A review of student recommendation systems in higher education. Artificial Intelligence Review, 54(2):1327–1364.
Norris, J. R. (1998). Markov Chains. Cambridge University Press.
Pandey, S. and Karypis, G. (2019). A self-attentive model for knowledge tracing. In IEEE International Conference on Data Mining (ICDM).
Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L., and Sohl-Dickstein, J. (2015a). Deep knowledge tracing. In Advances in Neural Information Processing Systems (NeurIPS), volume 28.
Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L., and Sohl-Dickstein, J. (2015b). Deep knowledge tracing. In Advances in Neural Information Processing Systems (NeurIPS), pages 505–513.
Quadrana, M. et al. (2018). Sequence-aware recommender systems. ACM Computing Surveys, 51(4):1–36.
Ricci, F., Rokach, L., and Shapira, B. (2015). Recommender Systems Handbook. Springer.
Romero, C. and Ventura, S. (2010). Educational data mining: A review of the state of the art. IEEE Transactions on Systems, Man, and Cybernetics, 40(6):601–618.
Salehi, M. and Haghighi, I. N. K. (2013). A course recommender system based on graduated students' experiences. In Proceedings of the 5th Conference on Information and Knowledge Technology (IKT), pages 139–144. IEEE.
Shen, J. et al. (2018). Inferring prerequisite structures from student data. IEEE Transactions on Learning Technologies, 11(2):195–208.
Siemens, G. (2013). Learning analytics: The emergence of a discipline. American Behavioral Scientist, 57(10):1380–1400.
Slim, A. et al. (2014). Curriculum bottlenecks and student progression. In EDM.
Tang, J. and Wang, K. (2018). Personalized top-n sequential recommendation via convolutional sequence embedding. In WSDM.
Viberg, O. et al. (2018). Current trends and issues in learning analytics. Computers in Human Behavior, 89:98–110.
Wu, Q. et al. (2021). Graph neural networks in recommender systems: A survey. ACM Computing Surveys, 55(5):1–37.
Ying, R. et al. (2018). Graph convolutional neural networks for web-scale recommender systems. In KDD.
Publicado
05/10/2026
Como Citar
MEDEIROS, Sarah A. da C.; BARROS, Abílio N.; MACIEL, Alexandre Magno A..
Uma Abordagem Baseada em Grafos e Aprendizado de Máquina para Recomendação Curricular em Engenharia. In: SIMPÓSIO BRASILEIRO DE INFORMÁTICA NA EDUCAÇÃO (SBIE), 37. , 2026, Goiânia/GO.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 1219-1232.
DOI: https://doi.org/10.5753/sbie.2026.27706.
