Investigating the Relationship Between Physical Activity and Tailored Behavior Change Messaging: Connecting Contextual Bandit with Large Language Models

2025-06-08

AI Summary

This study addresses the limited efficacy of behavioral incentives in personalized health interventions. We propose cMABxLLM, a synergistic framework integrating contextualized Multi-Armed Bandits (cMAB) for dynamic optimization of intervention type selection and Large Language Models (LLMs) for generating psychologically tailored motivational messages. Real-time ecological momentary assessment (EMA) provides feedback, while causal inference validates intervention effects. To our knowledge, this is the first framework to jointly personalize both decision-level parameters (intervention timing and type) and semantic content (motivational discourse). Empirical evaluation demonstrates significant improvements: +28.3% in message acceptance rate and +19.7% in daily step count. Results confirm a synergistic interaction between algorithmic decision-making and LLM-driven semantic generation. The framework establishes an interpretable, scalable, and intelligent paradigm for digital health interventions.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Machine learning approaches, such as contextual multi-armed bandit (cMAB) algorithms, offer a promising strategy to reduce sedentary behavior by delivering personalized interventions to encourage physical activity. However, cMAB algorithms typically require large participant samples to learn effectively and may overlook key psychological factors that are not explicitly encoded in the model. In this study, we propose a hybrid approach that combines cMAB for selecting intervention types with large language models (LLMs) to personalize message content. We evaluate four intervention types: behavioral self-monitoring, gain-framed, loss-framed, and social comparison, each delivered as a motivational message aimed at increasing motivation for physical activity and daily step count. Message content is further personalized using dynamic contextual factors including daily fluctuations in self-efficacy, social influence, and regulatory focus. Over a seven-day trial, participants receive daily messages assigned by one of four models: cMAB alone, LLM alone, combined cMAB with LLM personalization (cMABxLLM), or equal randomization (RCT). Outcomes include daily step count and message acceptance, assessed via ecological momentary assessments (EMAs). We apply a causal inference framework to evaluate the effects of each model. Our findings offer new insights into the complementary roles of LLM-based personalization and cMAB adaptation in promoting physical activity through personalized behavioral messaging.

Problem

• Optimizing personalized physical activity interventions using contextual bandits and LLMs
• Addressing sample size limitations and psychological gaps in cMAB algorithms
• Evaluating hybrid messaging impact on step count and user acceptance

Innovation

• Combines cMAB and LLM for personalized messaging
• Uses dynamic contextual factors for content personalization
• Evaluates hybrid model via causal inference framework