NLP-Digitox: An NLP and LLM-Driven Mobile Application for Managing Smartphone Overuse Among Students

Abstract

NLP-Digitox is a privacy-oriented mobile application designed to help college students manage excessive smartphone use through behavioral monitoring and personalized intervention. The system combines on-device smartphone usage tracking with Natural Language Processing (NLP), sentiment analysis, and Large Language Model (LLM)-based personalized nudging. It calculates usage drift against user-defined goals and classifies behavioral patterns into healthy, minor-drift, and significant-drift states. Based on these states, the system provides gamified motivation, personalized natural-language nudges, or optional escalation to parent/counselor dashboards. The application is implemented using Flutter with Kotlin-based Android services for usage monitoring and local VPN-based application and internet blocking. A preliminary three-week pilot involving 40 undergraduate students observed reductions in average daily screen time and short-form video usage. These results are preliminary and should not be interpreted as evidence of causal effectiveness because the pilot did not include a control group.