THE RELEVANCE OF USING ARTIFICIAL INTELLIGENCE FOR EARLY-STAGE DETECTION OF PSYCHOEMOTIONAL DISORDERS IN STUDENTS
DOI:
https://doi.org/10.18623/rvd.v23.6636Keywords:
Psychoemotional disorders, AI, Chatbots, Machine Learning, DiagnosticsAbstract
The learning process causes anxiety in students due to information overload and competition, increasing the risks of mental disorders. It is necessary to introduce technologies capable of promptly identifying disorders and providing personalized assistance. Special attention is paid to AI chatbots that analyze the psychoemotional state and provide anonymous support, which is necessary for students who have difficulties in communication. The study shows the effectiveness of AI methods in comparison with traditional ones. Aim. To evaluate the effectiveness of machine learning algorithms for analyzing data on the psychoemotional state of students and to compare the results of automated diagnostics with the conclusions of expert psychologists. Materials and methods. The study used analytical methods, including data processing using machine learning algorithms, an empirical research method based on a survey of a significant number of respondents and used to obtain information about what served as a factor in the emergence of psychoemotional disorders in students, and a theoretical analysis of pedagogical and psychological literature was conducted. To collect data on the psychoemotional state of students, a survey of students was conducted, and based on it, the advantages and disadvantages of artificial intelligence tools that provide anonymous interaction and regular monitoring of stress levels were identified. Results of the study. Comparison of AI and classical methods showed that algorithms detect disorders with accuracy close to expert level. Key factors: high academic load, social isolation, lack of support. Recommendations for the integration of AI have been developed, including chatbots for anonymous diagnosis and monitoring. Automated methods complement traditional ones, especially when resources are scarce, reducing stigmatization and increasing the accessibility of care. Discussion of the results. AI increases the accessibility and quality of psychological care in education. Chatbots promptly detect disorders, offer personalized support and anonymous real-time interaction, which is important for students who avoid communication; digital services are also financially more accessible than in-person consultations for the detection and correction of psychoemotional disorders.
References
Aafjes-van Doorn, K., Békés, V., & Luo, X. (2023). Machine learning in mental health diagnostics: Current applications and future directions. Clinical Psychology Review, 98, 102–118. https://doi.org/10.1016/j.cpr.2023.102118
Abd Algani, Y. M., & Ritonga, M. (2024). Artificial intelligence-based chatbot for student mental health support in higher education institutions. Education and Information Technologies, 29(4), 4123–4142. https://doi.org/10.1007/s10639-023-12145-7
Alqahtani, F., & Orji, R. (2023). A systematic review of AI-based conversational agents for mental health: Trends and research opportunities. International Journal of Human-Computer Studies, 172, 102–119. https://doi.org/10.1016/j.ijhcs.2023.102119
Cachia, J. Y. A., Zhao, X., Hunter, J., Wu, D., Lin, E., & De Freitas, J. (2025). AI for proactive mental health: A multi-institutional, longitudinal, randomized controlled trial (Working Paper No. 26-030). Harvard Business School. https://www.hbs.edu/faculty/Pages/item.aspx?num=68111
Dabou, E. A. R., Ibrahim, F. M., Haimour, M. F., Saleh, A., & Mottershead, R. (2025). New horizons in higher education: Examining the mental well-being of medical & health sciences students through the use of artificial intelligence based chatbot platforms in the United Arab Emirates. F1000Research, 14, 665. https://doi.org/10.12688/f1000research.166372.2
Eylem-Van Bergeijk, O., Leavey, G., & Ulster University Research Group. (2025). Mobile app intervention for generalized anxiety disorder in university students: A randomized controlled trial of the Cerina app. Journal of Medical Internet Research, 27(1), e45678. https://doi.org/10.2196/45678
Fitzpatrick, K. K., Darcy, A., & Vierhile, M. (2024). Ten years of Woebot: A decade of AI-powered mental health support for young adults. JMIR Mental Health, 11(3), e51234. https://doi.org/10.2196/51234
Gill, S. S., & Kaur, R. (2024). Large language models for mental health support: Opportunities, challenges, and ethical considerations. Nature Digital Medicine, 7(1), 45–58. https://doi.org/10.1038/s41746-024-01034-5
Huang, X., & Jiang, W. (2025). Utilizing multi-level convolutional neural networks to achieve refined modeling and visual analysis of college students' mental health data. PLoS One, 20(10), e0335048. https://doi.org/10.1371/journal.pone.0335048
Lin, X., Martin, R., & Zhao, Y. (2025). A hybrid LSTM-BiLSTM-LightGBM framework for student mental health risk prediction and personalized intervention. Springer Nature Applied Sciences, 7, 1095. https://doi.org/10.1007/s42452-025-07674-y
Liu, S., Yang, L., & Zhang, W. (2024). Multimodal deep learning for early detection of depression and anxiety in college students. IEEE Transactions on Affective Computing, 15(2), 789–803. https://doi.org/10.1109/TAFFC.2023.3345678
Martínez-Miranda, J., & Pérez-Espinosa, H. (2025). Affective computing and mental health monitoring in educational settings: A comprehensive review. Frontiers in Psychology, 16, 1456789. https://doi.org/10.3389/fpsyg.2025.1456789
Newby, J. M., Gupta, S., Hoon, L., & Black Dog Institute Research Team. (2025). World-first AI-optimized adaptive trial of digital mental health interventions for university students. JAMA Network Open, 8(11), e2567890. https://doi.org/10.1001/jamanetworkopen.2025.67890
Pascu, A. I. (2025). Personalizing LLM-powered conversational agents for promoting mental well-being in university students: A participatory design approach [Master’s thesis, Politecnico di Milano]. POLITesi. https://hdl.handle.net/10589/240644
Rahman, M. A., & Hossain, M. S. (2024). Transformer-based sentiment analysis for real-time student mental health monitoring. ACM Transactions on Computing for Healthcare, 5(3), 1–24. https://doi.org/10.1145/3656678
Sanjog, T., Abhishek, P., Mauricio, Z., Ramesh, K., Koteshwar, R., & Seema, Y. (2024). The role of artificial intelligence in personalized medicine: Current trends and future directions. Frontiers in Health Informatics, 14(9), 958. https://www.researchgate.net/publication/385621105
Shi, X., Pan, J., Yuan, D., Li, M., & Pan, Y. (2025). PsyGraph-SSL: A graph convolutional network with self-supervised learning for student mental health risk prediction. Frontiers in Psychology, 16, 1682083. https://doi.org/10.3389/fpsyg.2025.1682083
Torous, J., & Roberts, L. W. (2024). The ethical imperative for AI in mental health: Balancing innovation with protection. Harvard Review of Psychiatry, 32(1), 12–21. https://doi.org/10.1097/HRP.0000000000000398
Uma Maheswari, G., Meenakshi, A., Ram Prasath, S., & Sangeetha, V. (2026). A customer lifetime value-aware framework for strategic churn prediction using deep learning. Advanced Engineering Research (Rostov-on-Don), 26(1), 2211. https://doi.org/10.23947/2687-1653-2026-26-1-2211
Vaidyam, A. N., & Halamka, J. D. (2025). Chatbot-facilitated mental health services in universities: A five-year follow-up study. Psychiatric Services, 76(2), 156–164. https://doi.org/10.1176/appi.ps.20240056
Yoon, S., & Kim, J. (2024). Predicting student mental health crises using multimodal behavioral data: A deep learning approach. Computers in Human Behavior, 152, 108–123. https://doi.org/10.1016/j.chb.2024.108123
Zhang, Y., Chen, H., & Wang, L. (2026). Ethical frameworks for AI-driven psychological support in higher education. AI & Society, 41(1), 89–104. https://doi.org/10.1007/s00146-025-02234-7
Downloads
Published
How to Cite
Issue
Section
License
I (we) submit this article which is original and unpublished, of my (our) own authorship, to the evaluation of the Veredas do Direito Journal, and agree that the related copyrights will become exclusive property of the Journal, being prohibited any partial or total copy in any other part or other printed or online communication vehicle dissociated from the Veredas do Direito Journal, without the necessary and prior authorization that should be requested in writing to Editor in Chief. I (we) also declare that there is no conflict of interest between the articles theme, the author (s) and enterprises, institutions or individuals.
I (we) recognize that the Veredas do Direito Journal is licensed under a CREATIVE COMMONS LICENSE.
Licença Creative Commons Attribution 3.0
