Time2Stop: Adaptive and Explainable Human-AI Loop for Smartphone Overuse Intervention

Abstract

Despite a rich history of investigating smartphone overuse intervention techniques, AI-based just-in-time adaptive intervention (JITAI) methods for overuse reduction are lacking. We develop Time2Stop, an intelligent, adaptive, and explainable JITAI system that leverages machine learning to identify optimal intervention timings, introduces interventions with transparent AI explanations, and collects user feedback to establish a human-AI loop and adapt the intervention model over time. We conducted an 8-week field experiment (N=71) to evaluate the effectiveness of both the adaptation and explanation aspects of Time2Stop. Our results indicate that our adaptive models significantly outperform the baseline methods on intervention accuracy (>32.8\% relatively) and receptivity (>8.0\%). In addition, incorporating explanations further enhances the effectiveness by 53.8\% and 11.4\% on accuracy and receptivity, respectively. Moreover, Time2Stop significantly reduces overuse, decreasing app visit frequency by 7.0$\sim$8.9\%. Our subjective data also echoed these quantitative measures. Participants preferred the adaptive interventions and rated the system highly on intervention time accuracy, effectiveness, and level of trust. We envision our work can inspire future research on JITAI systems with a human-AI loop to evolve with users.

References in corpus (12)

• SMOTE: Synthetic Minority Over-sampling Technique
• Federated Learning: Challenges, Methods, and Future Directions
• Mobile social media usage and academic performance
• Self-Control in Cyberspace: Applying Dual Systems Theory to a Review of Digital Self-Control Tools
• How the Design of YouTube Influences User Sense of Agency
• Enabling hand gesture customization on wrist-worn devices
• Generalization and Personalization of Mobile Sensing-Based Mood Inference Models: An Analysis of College Students in Eight Countries
• SwitchTube: A Proof-of-Concept System Introducing "Adaptable Commitment Interfaces" as a Tool for Digital Wellbeing
• MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention
• NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation
• InteractOut: Leveraging Interaction Proxies as Input Manipulation Strategies for Reducing Smartphone Overuse
• DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensing

Cited by in corpus (4)

• MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention
• InteractOut: Leveraging Interaction Proxies as Input Manipulation Strategies for Reducing Smartphone Overuse
• Scrolling in the Deep: Analysing Contextual Influences on Intervention Effectiveness during Infinite Scrolling on Social Media
• What Social Media Use Do People Regret? An Analysis of 34K Smartphone Screenshots with Multimodal LLM