KMAN Publication Inc. (KMANPUB) Journal of Assessment and Research in Applied Counseling (JARAC) 8 Serial Number 30 2026 07 01 Explainable AI Modeling of Special Education Teachers’ Psychological Well-Being During Artificial Intelligence Integration: The Roles of Occupational Stress, Self-Regulation, and Technological Confidence Explainable AI Modeling of Special Education Teachers’ Psychological Well-Being During Artificial Intelligence Integration: The Roles of Occupational Stress, Self-Regulation, and Technological Confidence 1 16 EN Journal Article 2026 02 14 <table> <tbody> <tr> <td> <p><strong>Objective:</strong> This study aimed to develop an explainable artificial intelligence model for predicting psychological well-being among special education teachers during artificial intelligence integration by examining the roles of occupational stress, self-regulation, and technological confidence.</p> <p><strong>Methods and Materials: </strong>This quantitative, cross-sectional, predictive-correlational study was conducted among 318 special education teachers working in public and non-public exceptional schools in Tehran during the 2025–2026 academic year. Participants were selected through multistage cluster sampling. Data were collected using a demographic and professional information form, the Ryff Psychological Well-Being Scale, the Teacher Stress Inventory, the Short Self-Regulation Questionnaire, and the Computer Self-Efficacy Scale adapted to educational technology and artificial intelligence contexts. Data analysis included descriptive statistics, Pearson correlation, multiple linear regression, and supervised machine-learning modeling. Five predictive models were compared, including multiple linear regression, support vector regression, random forest regression, gradient boosting regression, and extreme gradient boosting regression. SHAP analysis was used to interpret feature importance and explain the final artificial intelligence model.</p> <p><strong>Findings: </strong>Psychological well-being was significantly and negatively correlated with occupational stress and significantly and positively correlated with self-regulation and technological confidence. The multiple regression model was significant, F(6, 311) = 73.71, p &lt; 0.001, and explained 58.7% of the variance in psychological well-being. Self-regulation was the strongest positive predictor, followed by occupational stress as a negative predictor and technological confidence as a positive predictor. Frequency of AI-supported tool use also significantly predicted psychological well-being, whereas teaching experience and educational level were not significant predictors. Among the machine-learning models, extreme gradient boosting showed the best performance, with the highest test R² of 0.73 and the lowest prediction error. SHAP analysis identified occupational stress, self-regulation, and technological confidence as the most influential features in the final model.</p> <p><strong>Conclusion: </strong>The findings indicate that special education teachers’ psychological well-being during artificial intelligence integration is primarily shaped by occupational stress, self-regulatory capacity, and technological confidence. Explainable artificial intelligence can provide an interpretable and practical framework for identifying psychological and technological factors that support teacher well-being.</p> </td> </tr> </tbody> </table> <p><strong><em>Keywords:</em></strong> <em>Explainable artificial intelligence; psychological well-being; special education teachers; occupational stress; self-regulation; technological confidence; artificial intelligence integration.</em></p> https://www.journals.kmanpub.com/index.php/jarac/article/download/5716/10772