KMAN Publication Inc. (KMANPUB) Journal of Assessment and Research in Applied Counseling (JARAC) 8 Serial Number 29 2026 04 01 LSTM-Based Longitudinal Prediction of Psychological Resilience: The Role of Self-Compassion, Meaning in Life, Cognitive Reappraisal, and Social Support LSTM-Based Longitudinal Prediction of Psychological Resilience: The Role of Self-Compassion, Meaning in Life, Cognitive Reappraisal, and Social Support 1 10 10.61838/kman.jarac.5237 EN Journal Article 2025 12 02 <table> <tbody> <tr> <td> <p><strong>Objective:</strong> The present study aimed to investigate the longitudinal prediction of psychological resilience using an LSTM-based deep learning model by examining the dynamic contributions of self-compassion, meaning in life, cognitive reappraisal, and social support over time.</p> <p><strong>Methods and Materials: </strong>This longitudinal study was conducted on 428 participants recruited from Canada, with 392 retained for final analysis across four time points over a 12-month period. Data were collected using validated self-report instruments, including the Connor–Davidson Resilience Scale, Self-Compassion Scale, Meaning in Life Questionnaire, Emotion Regulation Questionnaire (cognitive reappraisal subscale), and the Multidimensional Scale of Perceived Social Support. Data preprocessing included multiple imputation and sequence structuring for time-series analysis. The primary analytical approach involved the application of Long Short-Term Memory (LSTM) neural networks implemented in Python using TensorFlow and Keras. The dataset was divided into training, validation, and test sets (70/15/15), and model performance was evaluated using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R². SHAP analysis was conducted to determine the temporal importance of predictors.</p> <p><strong>Findings: </strong>The LSTM model demonstrated strong predictive performance (R² = 0.66, RMSE = 2.52), indicating substantial explained variance in psychological resilience. Self-compassion emerged as the most significant predictor (β ≈ .54, p &lt; .001), followed by social support (β ≈ .51, p &lt; .001), meaning in life (β ≈ .49, p &lt; .001), and cognitive reappraisal (β ≈ .43, p &lt; .001). Longitudinal analyses revealed significant increases in resilience and all predictor variables across time (p &lt; .01). SHAP results indicated that self-compassion and meaning in life showed increasing contributions over time, whereas social support demonstrated stronger early influence and cognitive reappraisal maintained a stable effect across all time points.</p> <p><strong>Conclusion: </strong>The findings highlight the dynamic and multifactorial nature of psychological resilience, emphasizing the central role of self-compassion and the evolving contributions of internal and external resources over time. The integration of LSTM modeling with explainable AI provides a robust framework for capturing temporal patterns and enhancing predictive accuracy in psychological research.</p> </td> </tr> </tbody> </table> https://journals.kmanpub.com/index.php/jarac/article/download/5237/9595