DopaSense: A Native Android Application for On-Device Usage Analytics and Heuristic Behavioral Scoring
Keywords:
Android UsageStatsManager, Behavioral scoring, Digital addiction detection, Digital wellbeing, Dopamine index, Mobile data analytics, Smartphone usage analyticsAbstract
The rapid growth of smartphones has significantly increased digital connectivity worldwide, but it has also raised concerns about excessive screen usage and digital addiction. This paper presents DopaSense, a native Android application designed to analyze smartphone usage behavior and provide real-time intervention for digital addiction management. Unlike traditional systems that rely on offline datasets or survey-based analysis, the proposed system performs continuous on-device monitoring using Android system services such as Usage Stats Manager and Accessibility Service. A heuristic behavioral scoring model is introduced to compute a Dopamine Score based on application usage duration and category weights. Additionally, an Addiction Risk Index is derived from total screen time using a normalized scaling approach. The system incorporates a self-healing background architecture using Work Manager and boot-time recovery mechanisms, ensuring uninterrupted operation even under aggressive OS constraints. Experimental results demonstrate that the system effectively captures real-world usage patterns and provides meaningful behavioral insights, enabling users to develop healthier digital habits.
References
Developers, “UsageStatsManager,” Android Developers. 2026.
Developers, “Data Layer,” Android Developers.
Developers, “Save Data in a Local Database Using Room,” Android Developers.
J. Han and M. Kamber, “Data Mining: Concepts and Techniques,” 3rd ed, ScienceDirect, 2012.
T. Davenport and J. Bean, Big Data and Analytics in Digital Behavior Analysis. New York, NY, USA: McGraw-Hill. 2018.
Android Developers, "Jetpack Compose UI Toolkit,"
GeeksforGeeks, “Introduction to TensorFlow Lite,” May 2021.
S. Likhith, C. Chitteti, M. Dharani, V. Nivedhitha, N. G. Geethika, and V. Godwin, “Machine Learning Model for Prediction of Smartphone Addiction,” 2024 International Conference on Expert Clouds and Applications (ICOECA), pp. 924–929, Apr. 2024.
G. L. Schroeder, R. Francisco, and J. L. V. Barbosa, “Digital Phenotyping for Problematic Technology Use: A Systematic Literature Review and Taxonomy,” Current Addiction Reports, vol. 13, no. 1, May 2026.
D. Miezah, T. Brew, M. A. Graham, and P. Obeng, “Smartphone Addiction Among University Students: A Scoping Review of Prevalence, Correlates and Impact,” Human Behavior and Emerging Technologies, no. 1, Jan. 2026.
T. D. W. Wilcockson, A. M. Osborne, and D. A. Ellis, “Digital detox: The effect of smartphone abstinence on mood, anxiety, and craving,” Addictive Behaviors, vol. 99, p. 106013, Dec. 2019.
