AI-Driven Personalized Positive Psychology Interventions for Enhancing User Psychological Resilience
Keywords:
artificial intelligence, positive psychology interventions, personalization, psychological resilience, well-beingAbstract
Digital positive psychology interventions (PPIs) are increasingly employed to enhance well-being and resilience, yet most existing systems remain static and insufficiently personalized. These limitations hinder adaptability, sustained engagement, and overall effectiveness. To address this gap, we propose an AI-driven personalized intervention framework that integrates user profiling, natural language processing, reinforcement learning-based feedback optimization, and explainable AI. The system dynamically tailors activities such as gratitude journaling, mindfulness practice, and strengths identification to each user's psychological profile. Empirical validation using synthetic datasets and a 10-week pilot study involving 210 participants demonstrates that the proposed framework outperforms both generic mobile applications and chatbot-based interventions. It achieved a 17.3% increase in life satisfaction (SWLS) and a 22.8% improvement in resilience (CD-RISC), with statistically significant results (p < 0.01). Ablation studies confirm the critical contribution of user profiling and adaptive feedback, while explainability enhances user trust and perceived autonomy. These findings suggest that integrating artificial intelligence with positive psychology offers a scalable, interpretable, and empirically effective pathway for promoting happiness and resilience-holding strong potential for deployment in educational, occupational, and clinical settings.
References
1. L. E. van Zyl, J. Gaffaney, L. van der Vaart, B. J. Dik, and S. I. Donaldson, "The critiques and criticisms of positive psychology: A systematic review," The Journal of Positive Psychology, vol. 19, no. 2, pp. 206-235, 2024. doi: 10.1080/17439760.2023.2178956.
2. J. Prescott, and S. Barnes, "Artificial intelligence positive psychology and therapy," Counselling and Psychotherapy Research, vol. 24, no. 3, pp. 843-845, 2024. doi: 10.1002/capr.12784.
3. A. Carr, L. Finneran, C. Boyd, C. Shirey, C. Canning, O. Stafford, and T. Burke, "The evidence-base for positive psychology interventions: a mega-analysis of meta-analyses," The Journal of Positive Psychology, vol. 19, no. 2, pp. 191-205, 2024. doi: 10.1080/17439760.2023.2168564.
4. S. Heshmati, C. Muth, Y. Li, R. W. Roeser, J. M. Smyth, J. Vandekerckhove, and Z. Oravecz, "Who benefits from mobile health interventions? A dynamical systems analysis of psychological wellbeing in early adults," Applied Psychology: Health and Well‐Being, vol. 17, no. 3, p. e70037, 2025. doi: 10.1111/aphw.70037.
5. S. Saboor, A. Medina, and L. Marciano, "Application of positive psychology in digital interventions for children, adolescents, and young adults: systematic review and meta-analysis of controlled trials," JMIR mental health, vol. 11, no. 1, p. e56045, 2024. doi: 10.2196/56045.
6. I. Zettler, and C. F. Strandsbjerg, "Personalized Interventions," Current Opinion in Psychology, 2025. doi: 10.1016/j.copsyc.2025.102147.
7. H. R. Saeidnia, S. G. Hashemi Fotami, B. Lund, and N. Ghiasi, "Ethical considerations in artificial intelligence interventions for mental health and well-being: Ensuring responsible implementation and impact," Social Sciences, vol. 13, no. 7, p. 381, 2024. doi: 10.3390/socsci13070381.
8. S. J. Heintzelman, K. Kushlev, and E. Diener, "Personalizing a positive psychology intervention improves wellbeing," Applied Psychology: Health and Well‐Being, vol. 15, no. 4, pp. 1271-1292, 2023. doi: 10.1111/aphw.12436.
9. A. C. Collins, G. D. Price, R. J. Woodworth, and N. C. Jacobson, "Predicting individual response to a web-based positive psychology intervention: a machine learning approach," The journal of positive psychology, vol. 19, no. 4, pp. 675-685, 2024. doi: 10.1080/17439760.2023.2254743.
10. J. C. Lauffenburger, E. Yom-Tov, P. A. Keller, M. E. McDonnell, K. L. Crum, G. Bhatkhande, and N. K. Choudhry, "The impact of using reinforcement learning to personalize communication on medication adherence: findings from the REINFORCE trial," npj Digital Medicine, vol. 7, no. 1, p. 39, 2024. doi: 10.1038/s41746-024-01028-5.
11. C. Doherty, R. Lambe, B. O'Grady, D. O'Reilly-Morgan, B. Smyth, A. Lawlor, and E. Tragos, "An Evaluation of the effect of app-based exercise prescription using reinforcement learning on satisfaction and exercise intensity: randomized crossover trial," JMIR mHealth and uHealth, vol. 12, p. e49443, 2024.
12. S. Nepal, A. Pillai, W. Campbell, T. Massachi, M. V. Heinz, A. Kunwar, and A. T. Campbell, "MindScape study: integrating LLM and behavioral sensing for personalized AI-driven journaling experiences," Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies, vol. 8, no. 4, pp. 1-44, 2024. doi: 10.1145/3699761.
13. J. W. Hung, A. Hartanto, A. Y. Goh, Z. K. Eun, K. S. Kasturiratna, Z. X. Lee, and N. M. Majeed, "The efficacy of incorporating Artificial Intelligence (AI) chatbots in brief gratitude and self-affirmation interventions: Evidence from two exploratory experiments," Computers in Human Behavior: Artificial Humans, vol. 4, p. 100151, 2025. doi: 10.1016/j.chbah.2025.100151.
14. F. Jing, "AI psychotherapists and positive psychology: a systematic literature review of current literature and future directions," 2024.
15. H. Hou, I. Liu, F. Kong, and S. Ni, "Computational positive psychology: advancing the science of wellbeing in the digital era," The Journal of Positive Psychology, vol. 20, no. 1, pp. 1-14, 2025. doi: 10.1080/17439760.2024.2362443.
