Therapeutic Chatbot for Suicidal Risk Teens Using Large Language Models

Romero-Florida J.; Nolasco-Morales A.; Aures-Garcia A.; Bravo-Obando M.; Balvín-Landeo A. · Proceedings of the 2025 IEEE 32nd International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2025 (2025) · DOI: 10.1109/intercon67304.2025.11244711

Resumen

Suicide poses a significant public health risk that disproportionately affects young people between the ages of 15 and 34. For this reason, this research proposes the development of an autonomous chatbot based on Large Language Models (LLMs) as a tool to detect and prevent suicidal thoughts in adolescents, in collaboration with the Peruvian Center for Suicidology and Suicide Prevention (SENTIDO). In addition, the chatbot integrates new advanced natural language processing technologies with cognitive-behavioral therapy to provide 80% emotional support in a personalized and accessible way 24 hours a day.

Instituciones: Universidad Nacional Mayor de San Marcos; Universidad Peruana de Ciencias Aplicadas