Detection of Anxiety in Telematics Engineering Students Using an Artificial Intelligence-Based System

Abstract

Academic anxiety is an emerging concern for students in demanding engineering fields such as Telematics, which impacts both their academic performance and mental well-being. This study aims to develop an AI-based system to continuously monitor and, in real time, detect symptoms of anxiety. Using a qualitative-quantitative mixed method approach, a sample of 103 students was analyzed through validated surveys and the Zung test. The findings showed that 91% of the subjects have some level of anxiety. This was associated with academic workload (94% considered it high), intense pressure to meet deadlines (94%), and insufficient time for personal activities (54%). In response to these findings, SerenIA, a mobile application incorporating GPT-4, was designed to assess conversations via text/voice and generate reports that can be reviewed by mental health specialists. The tool demonstrated accurate detection of anxiety monitoring algorithms based on the Zung test, an accessible interface with multimodal interaction, and automatic generation of clinical report texts. The findings highlight the potential of AI for proactive risk management in early intervention care, ultimately mitigating the risks of student dropout or underachievement. This model is the first of its kind, integrating technology and psychology, providing a scalable solution for educational institutions