Improving the Well-Being of Financially Stressed University Students: A CBT-Based AI Chat-bot Intervention (Preprint)

Abstract

BACKGROUND Mental health concerns, particularly depression, anxiety, and loneliness, are prevalent among university students, with financial stress further compounding these issues. This study investigates the efficacy of a CBT-based AI chatbot in improving the well-being of financially stressed university students. OBJECTIVE This study investigates the efficacy of a CBT-based AI chatbot in improving the well-being of financially stressed university students. METHODS In this randomized controlled trial, 100 university students aged 18-24 years were randomly allocated to an intervention (n=50) or waitlist control group (n=50). The intervention group interacted with a CBT-based AI chatbot for seven consecutive days, receiving personalized support and coping strategies to alleviate psychological distress. Anxiety, depression, and loneliness were assessed at baseline, Day 3, and Day 7 using the Generalized Anxiety Disorder 7-item (GAD-7), Centre for Epidemiologic Studies Depression (CES-D), and UCLA Loneliness Scale. RESULTS Compared to controls, the intervention group showed significant reductions in depression (F = 8.48, p < .001) and loneliness (F = 4.69, p = .011) at Day 7 relative to baseline. GAD-7 scores did not show significant changes. The chatbot's effectiveness was moderated by financial stress, with participants with high baseline financial stress (PIFS scores above the median) demonstrating greater improvements in CES-D (F = 11.56, p < .001) and UCLA Loneliness scores (F = 11.18, p < .001) compared to those with low financial stress. CONCLUSIONS The CBT-based AI chatbot effectively reduced depression and loneliness in financially stressed university students. AI-driven interventions show promise in improving student mental health, especially for those facing financial hardship.