Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Qing He, Zeyu Wang, Yuzhou Du, Jiahuan Ding, Yuanchun Shi, Yuntao Wang

TL;DR

One of the first longitudinal evaluations of AI self-modeling in fitness engagement through a two-stage empirical study uncovered a catalyst effect that fostered early motivation through clear, attainable goals, followed by habituation and internalization which stabilized performance.

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.

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

TL;DR

One of the first longitudinal evaluations of AI self-modeling in fitness engagement through a two-stage empirical study uncovered a catalyst effect that fostered early motivation through clear, attainable goals, followed by habituation and internalization which stabilized performance.

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.
Paper Structure (74 sections, 4 equations, 10 figures, 5 tables)

This paper contains 74 sections, 4 equations, 10 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Background and Related Works
  3. Long-Term Behavior Change and Motivational Decline
  4. AI Self-Modeling as Personalized Nudging for Behavior Change
  5. Existing Works on AI Self-Modeling
  6. Theories and Principles Behind Self-modeling
  7. Fitness and Health as Context for Behavior Change
  8. AI Self-Modeling Nudging System Implementation
  9. Video Self-Modeling Pipeline
  10. Peer Model Preparation.
  11. Headshot Capture and Personalization.
  12. Face-swapping and Video Generation.
  13. Audio Self-Modeling Pipeline
  14. Voice Cloning.
  15. Response Generation.
  16. ...and 59 more sections

Figures (10)

  • Figure 1: System implementation for AI self-modeling. Interfaces are adapted from existing platforms and included for illustration only.
  • Figure 2: Two selected exercising tasks: (a) wall-sit, (b) crunch.
  • Figure 3: Overview of the experimental procedure for three groups (VSM, ASM, and Control). The diagram illustrates the sequential tasks on Day 1 and subsequent sessions on Day 2-Day 7.
  • Figure 4: Average performance change for VSM, ASM, and Control groups over 7 days.
  • Figure 5: Daily active participants during the 28-day intervention.
  • ...and 5 more figures