Recommendation system for anti-procrastination tracking based on ChatGPT and personal data

The purpose of the research is to analyze the potential of integrating the ChatGPT language model into a personalized  recommendation  system aimed at  reducing procrastination. The  focus  is on  the concept of a digital assistant capable of adaptively responding to users’ behavioral patterns, maintaining attention, and fostering self-discipline in the context of information overload and constant digital distractions. 
Methods. The system is based on the ChatGPT language model integrated with user activity trackers. It is designed to collect and analyze data such as task schedules, productivity levels, mood, task-switching frequency, and physiological parameters  (e.g., heart  rate, stress  level,  sleep quality) where wearable devices are available. The  system architecture includes a contextual layer for data aggregation and a dialogue generation module for personalized recommendations. Recommendations are stratified into operational (immediate actions), tactical (daily planning), and motivational (focus and resilience support) types. The system also provides mechanisms for adapting recommendations based on behavioral context, temporal patterns, and user state. 
Results. The paper describes the functional components of the proposed architecture, key user interaction scenarios, and examples of dialogue interventions. Interface solutions for visualizing progress in productivity and self-regulation are discussed. The feasibility of using a language model as an empathetic digital coach that can respond to users’ dynamic states and provide supportive guidance for overcoming procrastination is substantiated. 
Conclusion. The proposed concept demonstrates the potential of ChatGPT as a tool for digital well-being. Personalized interaction based on the analysis of user behavior and states may serve as a foundation for the development of effective digital self-regulation systems. Future research directions include the implementation of predictive logic, integration of biometric tracking, and expansion of the behavioral model. 

1. Smirnova T.A. Self-regulation and digital technologies: challenges and opportunities. Chelovecheskii kapital = Human Capital. 2022;(9):115–120. (In Russ.)

2. Dhamija S., Kumar R. Digital Wellbeing: A Review of Tools, Impact and Future Directions. IJIMAI. 2021;6:28–39.

3. Kuzmina Yu.V. Psychological aspects of procrastination and ways of their correction. Vestnik TvGU. Seriya: Pedagogika i psikhologiya = Vestnik TvGU. Series: Pedagogy and Psychology. 2020;(2):56–62. (In Russ.)

4. Steel P. The Procrastination Equation: How to Stop Putting Things Off and Start Getting Stuff Done. Random House of Canada; 2011. 352 p.

5. Gromov E.I. Procrastination as a phenomenon of the information society. Sotsiologiya vlasti = Sociology of Power. 2018;(5):142–148. (In Russ.)

6. Fogg B.J. Tiny Habits: The Small Changes That Change Everything. New York: Houghton Mifflin Harcourt; 2020. 306 p.

7. Kurtaev S.J. Digital well-being as a component of psychological stability in the digital environment. Psikhologiya i obshchestvo = Psychology and Society. 2021;(4):24–28. (In Russ.)

8. Baumeister R.F., Tierney J. Willpower: Rediscovering the Greatest Human Strength. New York: Penguin Books; 2012. 291 p.

9. Makarova N.A. Model of adaptive decision support in learning systems with AI. Informatsionnye tekhnologii = Information Technologies. 2020;(7):35–41. (In Russ.)

10. GPT-4. Available at: https://openai.com/research/gpt-4 (accessed 27.03.2025).

11. Malysheva O.N. Empathic AI systems: prospects and limitations of application in the field of digital coaching. Voprosy psikhologii = Issues of Psychology. 2021;(6):98–107. (In Russ.)

12. Wu Y., Chen H. Enhancing Productivity through Personalized AI Assistants: Design Principles. In: HCI International 2022 – Late Breaking Papers: Ergonomics and Product Design. 24th International Conference on Human-Computer Interaction, HCII 2022, Virtual Event, 26 June – 1 July 2022. Cham: Springer; 2022. P. 387–403.

13. Zhang Y., Chen X. Explainable Recommendation: A Survey and New Perspec-tives. Foundations and Trends in Information Retrieval. 2020;14:1–101.

14. Shevchenko A.A. Recommendation systems: principles, algorithms and methods. Vestnik Novosibirskogo gosudarstvennogo universiteta = Bulletin of Novosibirsk State Uni- versity. 2019;17(2):78–91. (In Russ.)

15. Pang G., Shen C., Cao L., Hengel A. van den. Deep Learning for Anomaly Detection: A Review. ACM Computing Surveys. 2021;54:1–38.

16. Ribeiro M.T., Singh S., Guestrin C. "Why should I trust you?": Explaining the Predictions of Any Classifier. Available at: https://arxiv.org/abs/1602.04938 (accessed 11.03.2025).

17. Kholodnaya M.A. Intellectual resources of personality: structure, diagnosis, development. Saint Petersburg: Piter; 2017. (In Russ.)

18. Stepanov I.V., Antipova N.M. Information fatigue and digital self-regulation: challenges of the digital age. Psikhologiya obrazovaniya v XXI veke = Psychology of Education in the 21st century. 2021;(2):90–97. (In Russ.)

19. Zeng Z., Wei Y. Emotion-Aware Intelligent Systems: A Survey. ACM Transactions on Interactive Intelligent Systems. 2020;10:12.

20. Stawarz K., Cox A.L., Blandford A. Beyond Self-Tracking and Reminders: De-signing Smartphone Apps That Support Habit Formation. In: CHI '15: Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems. Seoul, South Korea; 2015. P. 2653–2662. https://doi.org/10.1145/2702123.2702230