[论文解读] Does Personalized Nudging Wear Off? A Longitudinal Study of AI Self-Modeling for Behavioral Engagement

Qing He, Zeyu Wang+4 more|arXiv (Cornell University)|Feb 27, 2026

Behavioral Health and Interventions被引用 0

一句话总结

本研究纵向评估视频与音频AI自我建模作为个性化激励手段以维持健身参与度，结果表明视频自我建模在早期带来提升但趋于衰减但可维持表现，而音频自我建模效果较弱。

ABSTRACT

Sustaining the effectiveness of behavior change technologies remains a key challenge. AI self-modeling, which generates personalized portrayals of one's ideal self, has shown promise for motivating behavior change, yet prior work largely examines short-term effects. We present one of the first longitudinal evaluations of AI self-modeling in fitness engagement through a two-stage empirical study. A 1-week, three-arm experiment (visual self-modeling (VSM), auditory self-modeling (ASM), Control; N=28) revealed that VSM drove initial performance gains, while ASM showed no significant effects. A subsequent 4-week study (VSM vs. Control; N=31) demonstrated that VSM sustained higher performance levels but exhibited diminishing improvement rates after two weeks. Interviews uncovered a catalyst effect that fostered early motivation through clear, attainable goals, followed by habituation and internalization which stabilized performance. These findings highlight the temporal dynamics of personalized nudging and inform the design of behavior change technologies for long-term engagement.

研究动机与目标

• 使用AI生成的自我模型来激发长期健身参与。
• 将两种AI自我建模模态（视频与音频）与对照组进行比较。
• 考察激励效应及习惯形成的时间动态。
• 识别影响AI自我建模干预持久性的设计因素。

提出的方法

• 进行两阶段的经验评估：1周的探索性研究（N=28）和4周的随访研究（N=31）。
• 基于现有 pipelines 构建的视频自我建模（VSM）与音频自我建模（ASM）实现（FakeForward、Visomaster、ElevenLabs）。
• 客观指标：壁坐持续时间和仰卧起坐重复次数，按第1天基线归一化。
• 主观指标：在第1天和第7天（第2–6天缩短）使用IMI、ESES和VAIQ问卷。
• 采用线性混合效应模型评估持续表现及随时间的速率变化。

Figure 1 . The nudging effect of AI self-modeling across time and modalities in fitness. (a) Change of nudging effect of video self-modeling(VSM): users are motivated by the AI self-model at first, then grow numb to the repeating VSM intervention, yet the motivated self-model has internalized as the

实验结果

研究问题

• RQ1 AI自我建模是否能在日常健身实践中长期维持表现？
• RQ2 AI自我建模是否能持续提升速率？
• RQ3 哪些设计因素影响AI自我建模在行为改变方面的长期影响？

主要发现

• VSM在7天周期内初始改进更快，但增益趋于衰减。
• ASM显示改进不够稳定，未持续优于对照组。
• 对照组在一周内表现出稳定的自然进步，表明练习效应而非激励的影响。
• 4周内，VSM维持更高的表现，但大约两周后改善速率逐渐下降。
• 访谈显示对持续VSM的习惯化，但目标的内在化仍然存在。

Figure 2 . System implementation for AI self-modeling. Interfaces are adapted from existing platforms and included for illustration only.