Digital Environmental Sustainability Global Patterns of Psychological Responses to Natural Disasters

Natural disasters trigger diverse psychological responses, including anxiety, depression, fear, and resilience, yet disaster mental health research has largely centered on post-traumatic stress disorder (PTSD). This study investigates global patterns of mental health responses following major natural disasters using large-scale social media data. More than 450,000 publicly available posts related to floods, earthquakes, wildfires, and hurricanes between 2015 and 2025 were analyzed using natural language processing techniques, including sentiment analysis, emotion classification, and topic modeling. Distinct psychological response patterns were observed across disaster types. Wildfires generated the highest levels of anxiety-related expressions, whereas earthquakes produced intense but short-lived distress. Floods were characterized by prolonged discussions of stress and uncertainty, reflecting extended recovery challenges. Negative emotions peaked immediately after disaster occurrence and gradually declined over time, while expressions of social support and resilience increased throughout the recovery period. Regional differences further underscored the influence of socioeconomic conditions and cultural contexts on psychological outcomes. These findings demonstrate the potential of social media and artificial intelligence for real-time monitoring of disaster-related mental health. By moving beyond PTSD-focused assessments, this study provides a more comprehensive understanding of the evolution of anxiety, depression, and emotional resilience following natural disasters and offers a scalable framework to inform mental health interventions, disaster preparedness, and long-term recovery planning worldwide.