This research seeks to apply natural language processing (NLP) to predict psychological adjustment during continuous mass trauma, focusing on the Israel-Hamas War. By analyzing participants’ open-ended text responses, we will extract key emotional and behavioral indicators to develop predictive models for depression, anxiety, PTSD, and post-traumatic growth (PTG). The study aims to examine the added value that these text-based insights provide beyond traditional self-report measures, shedding light on both maladaptive and adaptive responses to trauma. Our research takes a longitudinal approach, capturing emotional and psychological changes over time to understand the processes that contribute to both psychological distress and resilience. By exploring the interplay between post-traumatic stress and growth, we aim to clarify the factors that promote recovery and adaptive responses amidst continuous trauma. With three large-scale samples (total N~16,000), and by utilizing cutting-edge machine learning techniques, this research offers a unique contribution to the field of trauma research. It has the potential to advance the field by integrating innovative, language processing methodologies, offering deeper insights into both individual differences in susceptibility and population-level mental health during times of prolonged conflict, and informing future interventions designed to support psychological recovery and resilience.