Development of a Chatbot Powered by Artificial Intelligence to Diagnose and Improve Stress and Anxiety Levels in University Students

De La Puente G.; Silva A.; Felix R. · Proceedings of the 2024 IEEE 31st International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2024 (2024) · DOI: 10.1109/intercon63140.2024.10833503

Resumen

Stress and anxiety among university students have become a significant issue, negatively impacting their academic performance and personal lives. To address this problem, an AI-powered chatbot was developed to provide personalized support based on Cognitive Behavioral Therapy (CBT) techniques. The chatbot offers multimodal interaction, cross-platform availability, and a user-centric design to enhance accessibility and engagement. An experiment was conducted with 47 Peruvian university students aged 19-26 to assess the chatbot's usability using the System Usability Scale (SUS). The results revealed an average SUS score of 82.13, indicating high usability compared to other digital health applications and chatbots, and promising stress and anxiety levels reduction, measured with the GAD-7 and PSS-14 surveys. The chatbot's effectiveness may vary among individuals, and ongoing research and optimization are necessary. However, this innovative solution demonstrates the potential of AI-driven chatbots in providing accessible mental health support for university students, contributing to their overall well-being and academic success.

Instituciones: Universidad Peruana de Ciencias Aplicadas