Does Personalized Nudging Wear Off? A Longitudinal Study of AI Self-Modeling for Behavioral Engagement

2026-02-27

AI Summary

The long-term efficacy of personalized nudges remains unclear. This study presents the first mixed-methods evaluation of AI-generated visual (VSM) and auditory self-modeling (ASM) through a two-phase longitudinal experiment, combining controlled trials with in-depth interviews to examine their sustained impact on physical activity. Results indicate that VSM significantly maintained exercise performance over four weeks, though the rate of improvement decelerated after two weeks; ASM showed no significant effects. The findings reveal a dynamic mechanism underlying personalized nudges—characterized by initial catalysis followed by habituation and internalization—and identify a critical temporal window for motivational transition. These insights challenge conventional assumptions about the static effectiveness of behavioral interventions.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Mechanism Design

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Economics, Online Markets and Human Computation: Sustainability of Web economics

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.

Problem

• personalized nudging
• behavior change
• long-term engagement
• AI self-modeling
• habituation

Innovation

• AI self-modeling
• personalized nudging
• longitudinal study
• behavioral engagement
• visual self-modeling