AI-Based Digital Addiction & Screen-Time Behavior Analyzer

This paper presents the design, implementation, and evaluation of an AI-powered system for real-time digital addiction detection and screen-time behavior analysis. The proposed system addresses the growing concern of excessive smartphone usage and its impact on mental health, academic performance, and workplace productivity. Existing solutions lack behavioral intelligence, real-time data extraction, and actionable intervention mechanisms. The platform integrates Android Debug Bridge (ADB)-based app usage extraction, a five-factor weighted machine learning (ML) risk scoring engine with sigmoid normalization, and a large language model (LLM)-powered insight generation module using Groq's LLaMA 3.3 70B to produce severity-rated behavioral recommendations. A Chrome Extension supplements the system by tracking browsing history in real time, enabling domain-level categorization and detection of inappropriate web content. Risk classification is performed across four levels — Minimal, Low, Moderate, and High — based on screen time, social media percentage, unlock frequency, night usage, and app concentration. A multi-channel alert system delivers warnings via ADB push notifications, ntfy real-time popups, and WhatsApp deep links when predefined thresholds are exceeded. The web dashboard renders hourly usage charts, app breakdowns, weekly trends, and a seven-day usage forecast powered by ARIMA time-series modeling. All data is persistently stored in Firebase Firestore with real-time synchronization. Experimental results confirm an average app usage detection accuracy of 97.5%, 100% risk classification accuracy across all four addiction levels, and sub-three-second AI response times. A dedicated ethics and privacy framework governs user consent, data storage, third-party API transmission, and compliance with GDPR and CCPA.

Android Debug Bridge, Behavioral Risk Scoring, Digital Addiction

1. J. Lee and W. Kim, "Prediction of problematic smartphone use: A machine learning approach," Int. J. Environ. Res. Public Health, vol. 18, no. 13, p. 6876, Jun. 2021. doi: 10.3390/ijerph18136876 [Google Scholar] [Crossref]

2. A.-M. Popescu, R.-Ş. Balica, and E. Lazăr, "Smartphone addiction risk, technology-related behaviors and psychological well-being," Front. Psychol., vol. 13, 840110, Mar. 2022. doi: 10.3389/fpsyg.2022.840110 [Google Scholar] [Crossref]

3. Y. Suh and J. Yoo, "Risk level prediction for problematic internet use: A digital health perspective," Internet Interv., vol. 39, 100754, Mar. 2025. doi: 10.1016/j.invent.2025.100754 [Google Scholar] [Crossref]

4. U. Lyngs et al., "Self-control in cyberspace: Applying dual systems theory to a review of digital self-control tools," in Proc. ACM CHI, Glasgow, UK, 2019, pp. 1–18. doi: 10.1145/3290605.3300361 [Google Scholar] [Crossref]

5. R. K. Ibrahim et al., "Screen time and stress: Digital burnout and health impact," BMC Nursing, vol. 24, no. 1, p. 198, Feb. 2025. doi: 10.1186/s12912-025-02198-3 [Google Scholar] [Crossref]

6. E. Duke and C. Montag, "Smartphone addiction, daily interruptions and self-reported productivity," Addict. Behav. Rep., vol. 6, pp. 90–95, Dec. 2017. doi: 10.1016/j.abrep.2017.07.002 [Google Scholar] [Crossref]

7. S. Namlı et al., "Smartphone and game addiction: Regression vs machine learning models," Healthcare, vol. 13, no. 4, p. 412, Feb. 2025. doi: 10.3390/healthcare13040412 [Google Scholar] [Crossref]

8. C. Joseph and P. Uma Maheswari, "Facial emotion based smartphone addiction detection using deep learning," Sci. Rep., vol. 15, no. 1, p. 4821, Feb. 2025. doi: 10.1038/s41598-025-87654-2 [Google Scholar] [Crossref]

9. A. Alkaabba et al., "Patterns of screen time, sleep quality, and mental health," Cureus J. Med. Sci., vol. 17, no. 1, e76543, Jan. 2025. doi: 10.7759/cureus.76543 [Google Scholar] [Crossref]

10. D. Wang et al., "A weighted feature scoring approach for mobile application risk assessment and behavioral classification," Comput. Hum. Behav., vol. 115, 106592, Feb. 2021. doi: 10.1016/j.chb.2020.106592 [Google Scholar] [Crossref]

11. H. Touvron et al., "LLaMA: Open and efficient foundation language models," arXiv preprint arXiv:2302.13971, Feb. 2023. [Google Scholar] [Crossref]

12. X. Yang et al., "Large language models in health and wellness: A systematic review of applications and evaluation," npj Digit. Med., vol. 7, no. 1, p. 45, Mar. 2024. doi: 10.1038/s41746-024-01032-9 [Google Scholar] [Crossref]

13. C. Xu et al., "AI-generated personalized feedback in digital wellness interventions: A randomized controlled trial," J. Med. Syst., vol. 48, no. 1, p. 12, Jan. 2024. doi: 10.1007/s10916-023-02021-3 [Google Scholar] [Crossref]

14. G. E. P. Box and G. M. Jenkins, Time Series Analysis: Forecasting and Control, 3rd ed. Englewood Cliffs, NJ: Prentice Hall, 1994. [Google Scholar] [Crossref]

15. S. J. Taylor and B. Letham, "Forecasting at scale," The Amer. Stat., vol. 72, no. 1, pp. 37–45, 2018. doi: 10.1080/00031305.2017.1380080 [Google Scholar] [Crossref]

16. B. Cao et al., "Deep learning-based classification of smartphone addiction using mobile usage data," J. Med. Internet Res., vol. 22, no. 10, e17541, Oct. 2020. doi: 10.2196/17541 [Google Scholar] [Crossref]

17. M. Kwon et al., "Development and validation of a smartphone addiction scale (SAS)," PLOS ONE, vol. 8, no. 2, e56936, Feb. 2013. doi: 10.1371/journal.pone.0056936 [Google Scholar] [Crossref]

18. Q. Gao et al., "Domain-level web content classification for behavioral analysis using keyword-based and machine learning approaches," Inf. Process. Manag., vol. 58, no. 3, 102512, May 2021. doi: 10.1016/j.ipm.2021.102512 [Google Scholar] [Crossref]

19. I. H. Sarker et al., "Mobile data science and intelligent apps: Concepts, AI-based modeling, and research directions," Mobile Netw. Appl., vol. 26, no. 3, pp. 285–303, Jun. 2021. doi: 10.1007/s11036-020-01650-z [Google Scholar] [Crossref]

20. A. Sha and M. Bahad, "Smartphone screen time tracking and behavioral intervention: A review of current approaches and future directions," IEEE Access, vol. 11, pp. 34521–34537, 2023. doi: 10.1109/ACCESS.2023.3264218 [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet