Mental Health Analysis System Using Large Language Model

Abstract

Traditional mental health surveys in educational settings often provide a limited perspective on students' mental well-being, relying on standardized questions that fail to capture the complexity and individuality of each student's experience. To address this, a system leveraging Large Language Models (LLMs) has been developed to dynamically generate personalized and adaptive questions in real time, based on students' previous responses. This personalized approach fosters deeper engagement and provides a more nuanced understanding of students’ mental health. The system's adaptive nature ensures that each student’s unique experiences and concerns are addressed, rather than relying on one-size-fits-all questionnaires. The data collected through this system is presented in an accessible, visually intuitive format, allowing educators to interpret the results quickly and effectively. This empowers them to adapt teaching strategies and implement targeted interventions that address specific mental health needs within the classroom. By integrating this system into educational settings, academic institutions can foster a more responsive and inclusive learning environment that prioritizes students' mental health. This approach not only enhances students' academic success but also promotes resilience and engagement by addressing mental health issues in real time. The system demonstrates the transformative potential of personalized AI in education, offering a scalable solution for improving student outcomes. It underscores the critical role of AI in creating healthier, more adaptive educational ecosystems capable of responding to the evolving mental health challenges faced by students today.