Artificial Intelligence Conversational Agent for Early Detection of Socioemotional Risk in Upper Secondary Education

Authors

Keywords:

Conversational agent, Artificial intelligence, Socioemotional risk, Upper secondary education, Student well-being

Abstract

This study aimed to design and implement an artificial intelligence-based pedagogical conversational agent to support the early detection of socio-emotional risk among upper secondary education students. The research adopted a mixed-methods approach with a descriptive-exploratory scope and an applied case study design conducted at CONALEP Lerma Campus, State of Mexico. A total of 74 students participated, and their open-ended responses were analyzed using Natural Language Processing (NLP), sentiment analysis, and rule-based classification techniques implemented in Python and RStudio. The results identified patterns associated with anxiety, sadness, emotional isolation, and academic stress, while also classifying different socio-emotional risk levels. Furthermore, the system generated empathetic responses aimed at preventive support. The findings suggest that artificial intelligence can strengthen institutional strategies for socio-emotional well-being and early detection processes in technical upper secondary education settings.

References

Bokolo, B. G., & Liu, Q. (2023). Deep learning-based depression detection from social media: Comparative evaluation of ML and transformer techniques. Electronics, 12(21), 4396. https://www.mdpi.com/2079-9292/12/21/4396

Comisión Nacional para la Mejora Continua de la Educación. (2023). Indicadores nacionales de la mejora continua de la educación en México 2023. MEJOREDU. https://www.mejoredu.gob.mx/publicaciones/informe-de-resultados/indicadores-nacionales

Holmes, W., Bialik, M., & Fadel, C. (2019). Artificial intelligence in education: Promises and implications for teaching and learning. Center for Curriculum Redesign. https://curriculumredesign.org/wp-content/uploads/AIED-Book-Excerpt-CCR.pdf

Instituto Nacional de Estadística y Geografía. (2024). Estadísticas de defunciones

registradas. INEGI. https://www.inegi.org.mx/programas/mortalidad/

Jurafsky, D., & Martin, J. H. (2023). Speech and language processing (3rd ed. draft).

Stanford University. https://web.stanford.edu/~jurafsky/slp3/

Le Glaz, A., Haralambous, Y., Kim-Dufor, D.-H., Martinez Perez, T., Saha, K., Amiri, S., Hickman, G., Lemogne, C., Buffel du Vaure, C.,

Shankardass, K., Llorca, P. M., & Lemey, C. (2021). Machine learning and natural language processing in mental health: Systematic review. Journal of Medical Internet Research, 23(5), e15708. https://pubmed.ncbi.nlm.nih.gov/33944788/

Luckin, R., Holmes, W., Griffiths, M., & Forcier, L. B. (2016). Intelligence unleashed: An

argument for AI in education. Pearson Education. https://discovery.ucl.ac.uk/id/eprint/1475756/

Organisation for Economic Co-operation and Development (OECD). (2023). Is education losing the race with technology? AI's progress in maths and reading. OECD Publishing. https://doi.org/10.1787/73105f99-en

Secretaría de Educación Pública. (2019).La Nueva Escuela Mexicana: Principios y

orientaciones pedagógicas. Gobierno de México. https://dfa.edomex.gob.mx/sites/dfa.edomex.gob.mx/files/files/NEM%20principios%20y%20orientacio%C3%ADn%20pedago%C3%ADgica.pdf

UNESCO. (2023). Guidance for generative AI in education and research. UNESCO Publishing. https://unesdoc.unesco.org/ark:/48223/pf0000386693

Vistorte, A. O. R., Deroncele-Acosta, A., Ayala, J. L. M., Barrasa, A., López-Granero, C., & Martí-González, M. (2024). Integrating artificial intelligence to assess emotions in learning environments: A systematic literature review. Frontiers in Psychology, 15, Article 1387089. https://doi.org/10.3389/fpsyg.2024.1387089.

World Health Organization. (2022). World mental health report: Transforming mental

health for all. World Health Organization. https://www.who.int/publications/i/item/9789240049338

Published

2026-06-25

How to Cite

Gámez Mora, D. J. N., & Pueblas Cornejo, M. M. (2026). Artificial Intelligence Conversational Agent for Early Detection of Socioemotional Risk in Upper Secondary Education. Revista Electrónica Desafíos Educativos, 5(Número Especial). Retrieved from https://redeci.ciinsev.edu.mx/index.php/portal/article/view/226