Problematic smartphone use negatively affects physical and mental health. Despite the wide range of prior research, existing persuasive techniques are not flexible enough to provide dynamic persuasion content based on users' physical contexts and mental states. We first conducted a Wizard-of-Oz study (N=12) and an interview study (N=10) to summarize the mental states behind problematic smartphone use: boredom, stress, and inertia. This informs our design of four persuasion strategies: understanding, comforting, evoking, and scaffolding habits. We leveraged large language models (LLMs) to enable the automatic and dynamic generation of effective persuasion content. We developed MindShift, a novel LLM-powered problematic smartphone use intervention technique. MindShift takes users' in-the-moment app usage behaviors, physical contexts, mental states, goals \& habits as input, and generates personalized and dynamic persuasive content with appropriate persuasion strategies. We conducted a 5-week field experiment (N=25) to compare MindShift with its simplified version (remove mental states) and baseline techniques (fixed reminder). The results show that MindShift improves intervention acceptance rates by 4.7-22.5% and reduces smartphone usage duration by 7.4-9.8%. Moreover, users have a significant drop in smartphone addiction scale scores and a rise in self-efficacy scale scores. Our study sheds light on the potential of leveraging LLMs for context-aware persuasion in other behavior change domains.

翻译：问题性智能手机使用对身心健康产生负面影响。尽管已有广泛研究，现有说服技术仍缺乏灵活性，无法根据用户的身体情境和心理状态提供动态说服内容。我们首先开展了一项"巫师之奥兹"研究（N=12）和一项访谈研究（N=10），归纳出问题性智能手机使用背后的心理状态：无聊、压力和惯性。这指导我们设计了四种说服策略：理解、安抚、唤起和习惯构建。我们利用大语言模型（LLMs）实现说服内容的自动动态生成，开发了MindShift——一种新颖的基于LLM的问题性智能手机使用干预技术。MindShift以用户即时应用使用行为、身体情境、心理状态、目标与习惯为输入，通过恰当的说服策略生成个性化动态说服内容。我们开展了为期五周的实地实验（N=25），将MindShift与其简化版本（去除心理状态）及基线技术（固定提醒）进行对比。结果表明，MindShift将干预接受率提升4.7%-22.5%，智能手机使用时长减少7.4%-9.8%。同时，用户智能手机成瘾量表评分显著下降，自我效能感量表评分显著上升。本研究揭示了利用LLM在其他行为改变领域实现情境感知说服的潜力。