AI日记提示对他人相关行为效果差，自控行为更易改变。
Not All Nudges Land: Behavioral Controllability and Elaboration Quality in AI-Supported Journaling
- 基于26个传感器特征分析用户日记，判断行为改变响应度。
- 独自可执行的行为改善率最高达63%，依赖他人者仅15%-22%。
- 写作质量影响有限，仅特定行为（如短信）和长篇个人意图有效。
AI日记工具可根据个体感知行为定制提示，但尚不清楚哪些行为能响应。我们分析了为期八周被动传感研究中的369篇日记，利用大语言模型（LLM）标注每篇是否表达改变行为的意图，并通过3天前后对比26个传感器特征评估实际改变。响应度最依赖行为是否涉及他人：依赖他人的行为改善率仅15%至22%，而个人可独立行动的行为改善率可达50%至63%，但结果不均。写作方式影响较小——无单一文本特征能区分改善与未改善条目；文字信号仅在特定行为中显现，尤其在短信行为及更长、更私密的意图表达中最为明显。样本量较小，这些发现为探索性模式，提示AI日记提醒最可能奏效于个人可控行为。
原文摘要 · Abstract (English)
AI journaling tools can tailor prompts to a person's own sensed behavior, but it is unclear which behaviors respond to them. We analyzed 369 journal entries from an eight-week passive sensing study. An LLM labeled each entry as expressing an intention to change a behavior or not, and we measured follow-through against 26 sensor features with a 3-day before/after comparison. Responsiveness depended most on whether a behavior involves other people. Behaviors that depend on others improved in only 15 to 22% of cases, while behaviors a person can act on alone improved more often, up to 50 to 63%, though unevenly. How users wrote mattered less. No single text feature separated improved from unimproved entries; writing carried signal only within specific behaviors, most clearly for text messaging and for longer, more personal intention entries. The sample is small, so we treat these as exploratory patterns that point to where AI journaling nudges are most likely to work.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。