Saltar al contenido
República del Perú · Observatorio de la producción científica universitaria
OApol.org Observatorio de Inteligencia Científica Universitaria del Perú
OApol.org
Inicio Universidades Publicaciones Investigadores
Repositorios
Tesis y trabajos académicosRevistas
Indicadores
Ranking trimestralRanking por carreraObjetivos de Desarrollo SostenibleReporte OCDERed neuronal 3D
Acerca
MetodologíaPrivacidad

EXPLORATORY PILOT STUDY OF AN ARTIFICIAL INTELLIGENCE-BASED CHATBOT FOR INITIAL MENTAL HEALTH SUPPORT AMONG UNIVERSITY STUDENTS

Sánchez Carlessi H.H.; Piedra Rubio L.H.; Galván Ayala G.A. · Revista de la Facultad de Medicina Humana (2026) · DOI: 10.25176/rfmh.v26i2.8526

Resumen

Introduction: Mental health problems among university students justify the use of chatbots for initial support. Objectives: To develop and evaluate the feasibility, acceptability, perceived usefulness, and preliminary functioning of the URPI Chatbot among university students. Methods: An exploratory pilot study of development, feasibility, and acceptability was conducted. The initial sample included 217 students who completed the Psychosocial Behavioral Maladjustment Inventory 2025 (INDACPS-2025), which assessed anxiety, low self-esteem, depression, hopelessness, stress, uncertainty, and low willingness to study. Based on percentile norms, 36 students with high scores on at least three scales, at or above the 75th percentile, were purposively selected. Of these, 24 interacted with the URPI Chatbot through the WhatsApp Cloud API for six weeks. The tool used generative artificial intelligence and natural language processing, and 12 students completed the anonymous satisfaction survey. Results: The URPI Chatbot recorded 1,580 messages, representing a 239% increase compared with the web-based pilot version. The conversations were predominantly related to anxiety and academic stress (34%), sadness and hopelessness (25%), self-esteem and self-worth (14%), family and interpersonal relationships (13%), procrastination or lack of motivation (9%), and other topics (5%). Consistently, emotional tension accounted for 40%, discouragement or loss of energy for 35%, and low self-efficacy for 25%. In the survey, most participants reported ease of use, partial usefulness, and willingness to recommend the tool. Conclusion: The URPI Chatbot showed preliminary feasibility, favorable acceptability, and perceived usefulness as a complementary tool for initial mental health support among university students. Artículo publicado por la Revista de la Facultad de Medicina Humana de la Universidad Ricardo Palma. Es un artículo de acceso abierto, distribuído bajo los términos de la Licencia Creative Commons: Creative Commons Attribution 4.0 International, CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), que permite el uso no comercial, distribución y reproducción en cualquier medio, siempre que la obra original sea debidamente citada. Para uso comercial, por favor póngase en contacto con revista.medicina@urp.pe

Instituciones: Universidad Ricardo Palma