Resumen
Este estudio aplica un enfoque de analítica del aprendizaje y modelos explicables para identificar contenidos de mayor dificultad en matemáticas universitarias a partir de registros de interacción de una plataforma de práctica y evaluación. Se realizó un análisis cuantitativo secundario del conjunto de datos MathE, considerando variables de contenido (tema, subtema y palabras clave) y contexto (país y nivel). Primero se estimaron tasas de error por tema y subtema y se sintetizaron patrones mediante visualizaciones comparativas. Luego se entrenaron modelos complementarios, una regresión logística por su interpretabilidad y un modelo no lineal de árboles de gradiente para capturar interacciones, validando la generalización con partición por estudiante. La explicabilidad se abordó mediante atribución de contribuciones para interpretar factores asociados al error. Los hallazgos señalan mayores dificultades en contenidos de Diferenciación, Interpretación Funcional y Probabilidad, junto con debilidades transversales de manipulación algebraica, con apoyos adicionales en Métodos Numéricos e Integración.
Citas
[2] G. J. Hwang and Y. F. Tu, “Roles and Research Trends of Artificial Intelligence in Mathematics Education: A Bibliometric Mapping Analysis and Systematic Review,” Mathematics 2021, Vol. 9, vol. 9, no. 6, Mar. 2021, doi: 10.3390/MATH9060584.
[3] H. Khosravi et al., “Explainable Artificial Intelligence in education,” Computers and Education: Artificial Intelligence, vol. 3, p. 100074, Jan. 2022, doi: 10.1016/J.CAEAI.2022.100074.
[4] B. F. Azevedo, M. F. Pacheco, F. P. Fernandes, and A. I. Pereira, “Dataset of mathematics learning and assessment of higher education students using the MathE platform,” Data Brief, vol. 53, p. 110236, Apr. 2024, doi: 10.1016/J.DIB.2024.110236.
[5] P. D. Long and G. Siemens, “Penetrare la nebbia: tecniche di analisi per l’apprendimento,” Revista Italiana de Tecnología Educativa, vol. 22, no. 3, pp. 132–137, Dec. 2014, doi: 10.17471/2499-4324/195.
[6] D. J. Lemay, C. Baek, and T. Doleck, “Comparison of learning analytics and educational data mining: A topic modeling approach,” Computers and Education: Artificial Intelligence, vol. 2, p. 100016, Jan. 2021, doi: 10.1016/J.CAEAI.2021.100016.
[7] A. Zeileis, “Examining Exams Using Rasch Models and Assessment of Measurement Invariance,” Austrian Journal of Statistics, vol. 54, no. 3, pp. 9–26, Sep. 2024, doi: 10.17713/ajs.v54i3.2055.
[8] Z. Zhang, “Model building strategy for logistic regression: purposeful selection,” Ann. Transl. Med., vol. 4, no. 6, p. 111, Mar. 2016, doi: 10.21037/ATM.2016.02.15.
[9] S. M. Lundberg and S. I. Lee, “A Unified Approach to Interpreting Model Predictions,” Adv. Neural Inf. Process. Syst., vol. 2017-December, pp. 4766–4775, May 2017, Accessed: Jan. 20, 2026. [Online]. Available: https://arxiv.org/pdf/1705.07874
[10] N. Bergdahl, M. Bond, J. Sjöberg, M. Dougherty, and E. Oxley, “Unpacking student engagement in higher education learning analytics: a systematic review,” International Journal of Educational Technology in Higher Education, vol. 21, no. 1, pp. 63-, Dec. 2024, doi: 10.1186/S41239-024-00493-Y/TABLES/6.
[11] D. Ifenthaler, · Jane, Y.-K. Yau, D. Ifenthaler, and Y.-K. Yau, “Utilising learning analytics to support study success in higher education: a systematic review,” Educational Technology Research and Development 2020 68:4, vol. 68, no. 4, pp. 1961–1990, Jun. 2020, doi: 10.1007/S11423-020-09788-Z.
[12] L. Paulsen and E. Lindsay, “Learning analytics dashboards are increasingly becoming about learning and not just analytics - A systematic review,” Education and Information Technologies 2024 29:11, vol. 29, no. 11, pp. 14279–14308, Jan. 2024, doi: 10.1007/S10639-023-12401-4.
[13] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol. 13-17-August-2016, pp. 785–794, Aug. 2016, doi: 10.1145/2939672.2939785.
[14] S. M. Lundberg et al., “From local explanations to global understanding with explainable AI for trees,” Nature Machine Intelligence 2020 2:1, vol. 2, no. 1, pp. 56–67, Jan. 2020, doi: 10.1038/s42256-019-0138-9.
[15] A. Barredo Arrieta et al., “Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI,” Information Fusion, vol. 58, pp. 82–115, Jun. 2020, doi: 10.1016/J.INFFUS.2019.12.012.

