Resumen
El presente estudio desarrolla un sistema inteligente basado en aprendizaje automático para la detección temprana del estrés académico en estudiantes universitarios, centrado en las áreas de Ingeniería y Ciencias Sociales. A partir de un enfoque cuantitativo y de simulación, se construyó un dataset estructurado que integra variables académicas, conductuales y psicosociales. Se implementaron modelos predictivos, incluyendo Random Forest, Support Vector Machines y XGBoost, evaluando su desempeño mediante métricas de clasificación multiclase y binaria. Los resultados evidencian que los modelos de ensamble alcanzan los mayores niveles de precisión, superando el 90% en la detección de niveles de estrés. Asimismo, se identificaron variables clave como el cansancio, la concentración, las tareas pendientes y las horas de sueño. La simulación de escenarios demostró que las intervenciones combinadas generan reducciones significativas en la probabilidad de estrés alto. El estudio aporta un enfoque predictivo-explicativo que contribuye a la toma de decisiones en entornos educativos orientados al bienestar estudiantil.
Citas
[2] E. Zaid, J. Qaddumi, H. Sabbagh, and F. Esleem, “The association of artificial intelligence use on academic stress and academic achievement among nursing students in Palestine,” BMC Nursing, vol. 25, no. 1, 2026. doi: 10.1186/s12912-026-04666-0.
[3] Z. Hamd et al., “Utilizing artificial intelligence to assess academic exam anxiety, perceived stress, and achievement motivation,” Frontiers in Psychiatry, vol. 17, 2026. doi: 10.3389/fpsyt.2026.1686106.
[4] A. Singh, K. Singh, A. Kumar, A. Shrivastava, and S. Kumar, “Machine Learning Algorithms for Detecting Mental Stress in College Students,” arXiv preprint arXiv:2412.07415, 2024. doi: 10.48550/arXiv.2412.07415.
[5] C. Janiesch, P. Zschech, and K. Heinrich, “Machine learning and deep learning,” Electronic Markets, vol. 31, no. 3, pp. 685–695, 2021. doi: 10.1007/s12525-021-00475-2.
[6] T. Baltrušaitis, C. Ahuja, and L.-P. Morency, “Multimodal Machine Learning: A Survey and Taxonomy,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 2, pp. 423–443, 2019. doi: 10.1109/TPAMI.2018.2798607.
[7] A. M. Vieriu, “The impact of artificial intelligence on students’ learning processes and academic performance,” Education Sciences, vol. 15, no. 3, p. 343, 2025. doi: 10.3390/educsci15030343.
[8] S. Sayici, “Balancing usefulness, stress, and cognitive load: Artificial intelligence tools in higher education,” Master’s thesis, Tilburg University, Netherlands, 2025. Available: https://arno.uvt.nl/show.cgi?fid=185574.
[9] R. Tariq et al., “Explainable artificial intelligence for predictive modeling of student stress,” Scientific Reports, vol. 15, 2025. doi: 10.1038/s41598-025-22171-3.
[10] D. Wang et al., “The roles of academic procrastination and help-seeking behavior in AI-supported educational environments,” Frontiers in Psychology, vol. 17, 2026. doi: 10.3389/fpsyg.2026.1578452.
[11] S. Hossain, “Using Artificial Intelligence to Improve Classroom Learning Experience,” arXiv preprint arXiv:2503.05709, 2025. doi: 10.48550/arXiv.2503.05709.
[12] B. Klimova et al., “Exploring the effects of artificial intelligence on student well-being, mental health, and academic engagement,” Frontiers in Education, vol. 10, 2025. doi: 10.3389/feduc.2025.1456721.
[13] V. Chandola, A. Banerjee, and V. Kumar, “Anomaly Detection: A Survey,” ACM Computing Surveys, vol. 41, no. 3, pp. 1–58, 2009. doi: 10.1145/1541880.1541882.
[14] I. T. Jolliffe, Principal Component Analysis, 2nd ed. New York, NY, USA: Springer, 2002. doi: 10.1007/b98835.
[15] J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. Waltham, MA, USA: Morgan Kaufmann, 2011. doi: 10.1016/C2009-0-61819-5.
