Recomendação Personalizada de Recursos Educacionais com Aprendizado de Máquina: Comparação Experimental entre Baselines Clássicos e SAKT
Resumo
Este artigo apresenta um estudo experimental sobre recomendação personalizada de recursos educacionais com dados de interações do ASSISTments. Comparamos recomendadores clássicos (Popularidade, Item-kNN e TruncatedSVD) com um modelo sequencial de knowledge tracing (SAKT) em um protocolo temporal de predição do próximo item. A avaliação utiliza HitRate@10, NDCG@10, Precision@10 e Recall@10 com 200 negativos amostrados por usuário de teste. Os baselines clássicos obtiveram os melhores resultados, enquanto o SAKT apresentou sinais de sobreajuste na execução com 20 épocas. O artigo discute implicações metodológicas, ameaças à validade e próximos passos para recomendação educacional.Referências
ASSISTments Data Mining (2024). Assistments dataset. [link]. Acesso em: 21 fev. 2026.
Comitê Gestor da Internet no Brasil (CGI.br) (2024). Sete em cada dez alunos do ensino médio usam ia generativa em pesquisas escolares, revela tic educação. [link]. Acesso em: 21 fev. 2026.
Halko, N., Martinsson, P.-G., and Tropp, J. A. (2011). Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions. SIAM Review, 53(2):217–288.
Heffernan, N. T. and Heffernan, C. L. (2014). Assistments ecosystem: Building a platform that brings scientists and teachers together for minimally invasive research on human learning and teaching. International Journal of Artificial Intelligence in Education, 24(4):470–497.
Instituto Nacional de Estudos e Pesquisas Educacionais Anísio Teixeira (Inep) (2024). Mec e inep contextualizam resultados do censo escolar 2024. [link]. Acesso em: 21 fev. 2026.
Koren, Y., Bell, R., and Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer, 42(8):30–37.
Li, Y. et al. (2024). Recent developments in recommender systems: A survey. IEEE Computational Intelligence Magazine.
Mhagama, J. T. and Garg, K. (2025). A systematic review of educational recommender systems: Techniques, target users, and emerging trends in personalized learning. International Journal of Technology in Education Science, 2(1):79–98.
Pandey, S. and Karypis, G. (2019). A self-attentive model for knowledge tracing. In Proceedings of the 12th International Conference on Educational Data Mining (EDM 2019), pages 384–389.
Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L., and Sohl-Dickstein, J. (2015). Deep knowledge tracing. In Advances in Neural Information Processing Systems (NeurIPS), volume 28.
Raza, S. et al. (2026). A comprehensive review of recommender systems. Journal of Network and Computer Applications.
Ricci, F., Rokach, L., and Shapira, B. (2022). Recommender Systems Handbook. Springer, 3 edition.
Sarwar, B., Karypis, G., Konstan, J., and Riedl, J. (2001). Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th International Conference on World Wide Web (WWW ’01), pages 285–295. ACM.
Shen, S., Liu, Q., et al. (2024). A survey of knowledge tracing: Models, variants, and applications. IEEE Transactions on Learning Technologies.
Wang, C., Ma, W., Zhang, M., Chen, C., Liu, Y., and Ma, S. (2021). Temporal cross-effects in knowledge tracing. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining. ACM.
Comitê Gestor da Internet no Brasil (CGI.br) (2024). Sete em cada dez alunos do ensino médio usam ia generativa em pesquisas escolares, revela tic educação. [link]. Acesso em: 21 fev. 2026.
Halko, N., Martinsson, P.-G., and Tropp, J. A. (2011). Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions. SIAM Review, 53(2):217–288.
Heffernan, N. T. and Heffernan, C. L. (2014). Assistments ecosystem: Building a platform that brings scientists and teachers together for minimally invasive research on human learning and teaching. International Journal of Artificial Intelligence in Education, 24(4):470–497.
Instituto Nacional de Estudos e Pesquisas Educacionais Anísio Teixeira (Inep) (2024). Mec e inep contextualizam resultados do censo escolar 2024. [link]. Acesso em: 21 fev. 2026.
Koren, Y., Bell, R., and Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer, 42(8):30–37.
Li, Y. et al. (2024). Recent developments in recommender systems: A survey. IEEE Computational Intelligence Magazine.
Mhagama, J. T. and Garg, K. (2025). A systematic review of educational recommender systems: Techniques, target users, and emerging trends in personalized learning. International Journal of Technology in Education Science, 2(1):79–98.
Pandey, S. and Karypis, G. (2019). A self-attentive model for knowledge tracing. In Proceedings of the 12th International Conference on Educational Data Mining (EDM 2019), pages 384–389.
Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L., and Sohl-Dickstein, J. (2015). Deep knowledge tracing. In Advances in Neural Information Processing Systems (NeurIPS), volume 28.
Raza, S. et al. (2026). A comprehensive review of recommender systems. Journal of Network and Computer Applications.
Ricci, F., Rokach, L., and Shapira, B. (2022). Recommender Systems Handbook. Springer, 3 edition.
Sarwar, B., Karypis, G., Konstan, J., and Riedl, J. (2001). Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th International Conference on World Wide Web (WWW ’01), pages 285–295. ACM.
Shen, S., Liu, Q., et al. (2024). A survey of knowledge tracing: Models, variants, and applications. IEEE Transactions on Learning Technologies.
Wang, C., Ma, W., Zhang, M., Chen, C., Liu, Y., and Ma, S. (2021). Temporal cross-effects in knowledge tracing. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining. ACM.
Publicado
19/07/2026
Como Citar
FABRES, Ana Clara; SANTOS, Carlos; VASCONCELLOS, Cristhiano.
Recomendação Personalizada de Recursos Educacionais com Aprendizado de Máquina: Comparação Experimental entre Baselines Clássicos e SAKT. In: ENCONTRO NACIONAL DE COMPUTAÇÃO DOS INSTITUTOS FEDERAIS (ENCOMPIF), 13. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 25-32.
ISSN 2763-8766.
DOI: https://doi.org/10.5753/encompif.2026.20734.
