From Detection to Conversation: Evolution of a Culturally Competent Emotional Support Chatbot
DOI:
https://doi.org/10.47187/perspectivas.8.1.252Keywords:
Artificial Intelligence, Emotional Health, Chatbot, LLM, Cultural Adaptation, Hybrid ModelAbstract
This paper presents the evolution of PsicoloBot, an emotional support chatbot developed with cultural competence for the Spanish-speaking population of Mexico. The study was conducted in two phases. In the first phase, a rule-based lexical detection algorithm was implemented, achieving an accuracy of 82% in emotion classification; however, it exhibited notable limitations in contextual understanding and dialogue quality. To ensure cultural adaptation, this phase required an extensive process of idiom mining from social media sources and data extraction, transformation, and loading (ETL). In the second phase, a hybrid architecture is proposed that integrates a Large Language Model (LLM), such as Google’s Gemini, to enhance contextual awareness. This architecture combines the efficiency and precision of the lexical engine with the generative capabilities of artificial intelligence, enabling interactions that more closely simulate empathetic and culturally relevant dialogue.
References
[1] Organización Mundial de la Salud. (2022). Salud mental del adolescente. Obtenido de https://www.who.int/es/news-room/fact-sheets/detail/adolescent-mental-health
[2] Descartes, R. (1649), Las pasiones del alma, Alianza Editorial, Madrid, España. Partes I y II.
[3] Bresó, E., Gabriela, M. R. Y. and Andriani, J. (2013), ‘La inteligencia emocional y la atención plena (mindfulness) como estrategia para la gestión de emociones negativas’, Psicogente 16 (30).
[4] Fitzpatrick, K. K., Darcy, A., & Vierhile, M. (2017). Delivering Cognitive Behavior Therapy to Young Adults With Symptoms of Depression and Anxiety Using a Fully Automated Conversational Agent (Woebot): A Randomized Controlled Trial. JMIR Mental Health, 4(2), e19.
[5] Denecke, K., Vaaheesan, S., & Arulnathan, A. (2021). A Mental Health Chatbot for Regulating Emotions (SERMO): Concept and Usability Test. IEEE Transactions on Emerging Topics in Computing, 9(3), 1170-1182.
[6] Mohammad, S. M. (n.d.). NRC Emotion Lexicon. National Research Council Canada. https://saifmohammad.com/WebPages/NRC-Emotion-Lexicon.htm
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yan Tepancal Martinez, María Santiago Díaz, Ana Zenteno Vázquez, Gustavo Rubín Linares
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright
The authors of the manuscripts will retain their copyright on their articles published in Pespectivas Journal. These rights allow the authors to present their manuscripts in public, prepare derivative works, reproduce them physically by printing and distribute them on their social or research networks. These rights will remain unchanged as long as the authors respect the publication and free access policy of Perspectivas Journal.
Publication Rights
Perspectivas Journal reserves all first publication rights on each of the articles that the authors have sent to its review and publication process. It implies that authors will only exercise their copyright if they state the source and origin of the publication correctly, mainly when they distribute, share, present, or use their articles' total or partial content.
