Automatic Knowledge Component Extraction to Bridge High School Knowledge Gaps for Engineering Students

• Mario Antonio Pessoa Santos Cogna Educação S.A.
• Mariana Nassif Cogna Educação S.A.
• Tyagi Lima Cogna Educação S.A.
• Filipe Dwan Pereira Universidade Federal de Roraima (UFRR) https://orcid.org/0000-0003-4914-3347
• André Nascimento Universidade Federal Rural de Pernambuco (UFRPE) https://orcid.org/0000-0002-9333-3212
• Luiz Rodrigues Universidade Tecnológica Federal do Paraná (UTFPR)
• Cleon Xavier Instituto Federal Goiano (IFGoiano) https://orcid.org/0000-0002-7617-5283
• Newarney Torrezão Costa Instituto Federal Goiano (IFGoiano) https://orcid.org/0000-0002-4954-176X
• Gabriel Alves Universidade Federal Rural de Pernambuco (UFRPE) https://orcid.org/0000-0002-2249-7818
• Rafael Ferreira Mello Universidade Federal Rural de Pernambuco (UFRPE) https://orcid.org/0000-0003-3548-9670

DOI: https://doi.org/10.5753/sbie.2026.27146

Resumo

Many students entering higher education have knowledge gaps from secondary education that contribute to low retention and high dropout rates. This short paper presents a case study that applies Knowledge Component (KC) extraction and recommendation techniques to help first-year engineering students bridge these gaps. Using embedding-based similarity methods, we mapped K–12 mathematical competencies to higher education prerequisites and delivered personalized preparatory resources through short video lectures and AI-generated summaries. Results indicate that the similarity-based approach achieved high validation rates in STEM-oriented disciplines, reliably identifying prerequisite KCs, while performance was less consistent in non-technical courses.

Palavras-chave: Knowledge Components, Recommendation Systems, Machine Learning

Referências

Abdelrahman, G., Wang, Q., and Nunes, B. (2023). Knowledge tracing: A survey. ACM Computing Surveys, 55(11):1–37.

Adachi, Y., Sakai, A., and Uehara, M. (2025). Cross-language semantic search using openai embedding. In 2025 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA), pages 1–6. IEEE.

Fan, J., Mihaylova, T., Akram, B., Norouzi, N., Brusilovsky, P., Hellas, A., and Leinonen, J. (2025). Adaptive learning curve analytics with llm-kc identifiers for knowledge component refinement. In Proceedings of the 2025 Conference on UK and Ireland Computing Education Research, pages 1–7.

Feinmann, J. and Hsu Rocha, R. (2024). Social mobility and higher education in brazil. Available at SSRN 4702937.

Ghadekar, P. P., Mohite, S., More, O., Patil, P., Mangrule, S., et al. (2023). Sentence meaning similarity detector using faiss. In 2023 7th International Conference On Computing, Communication, Control And Automation (ICCUBEA), pages 1–6. IEEE.

Koedinger, K. R., Corbett, A. T., and Perfetti, C. (2012). The knowledge-learning-instruction framework: Bridging the science-practice chasm to enhance robust student learning. Cognitive science, 36(5):757–798.

Pardos, Z. A. and Heffernan, N. T. (2010). Modeling individualization in a bayesian networks implementation of knowledge tracing. In International conference on user modeling, adaptation, and personalization, pages 255–266. Springer.

Pavlik Jr, P. I., Cen, H., and Koedinger, K. R. (2009). Learning factors transfer analysis: Using learning curve analysis to automatically generate domain models. Online Submission.

Rivers, K., Harpstead, E., and Koedinger, K. (2016). Learning curve analysis for programming: Which concepts do students struggle with? In Proceedings of the 2016 ACM Conference on International Computing Education Research, ICER '16, page 143–151, New York, NY, USA. Association for Computing Machinery.

Sampaio de Alencar, R., Demirtas, M. A., Saha, A. S., Shi, Y., and Brusilovsky, P. (2025). Integrating expert knowledge with automated knowledge component extraction for student modeling. In Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization, pages 307–312.

Scarlatos, A., Baker, R. S., and Lan, A. (2025). Exploring knowledge tracing in tutor-student dialogues using llms. In Proceedings of the 15th International Learning Analytics and Knowledge Conference, pages 249–259.

Schwartzman, S. (2004). Equity, quality and relevance in higher education in brazil. Anais da Academia Brasileira de Ciências, 76:173–188.

Shen, S., Liu, Q., Huang, Z., Zheng, Y., Yin, M., Wang, M., and Chen, E. (2024). A survey of knowledge tracing: Models, variants, and applications. IEEE Transactions on Learning Technologies, 17:1858–1879.

Shi, Y., Schmucker, R., Chi, M., Barnes, T., and Price, T. (2023). Kc-finder: Automated knowledge component discovery for programming problems. International Educational Data Mining Society.

Stavrinides, P. and Zuev, K. M. (2023). Course-prerequisite networks for analyzing and understanding academic curricula. Applied Network Science, 8(1):19.

Wong, C. S. Y. and Ramasamy, S. (2024). Architectural adaptation and regularization of attention networks for incremental knowledge tracing. In Proceedings of the 14th Learning Analytics and Knowledge Conference, pages 757–762.

Yang, M., Diao, M., Luo, J., Shen, W., and Zhang, C. (2025). Glm-4 based method for automatic construction of content graph. IEEE Access.

Zhang, X., Liu, S., and Wang, H. (2023). Personalized learning path recommendation for e-learning based on knowledge graph and graph convolutional network. International journal of software engineering and knowledge engineering, 33(01):109–131.