Potential of large language model-powered nudges for promoting daily water and energy conservation

2025-03-14

AI Summary

Traditional utility consumption interventions suffer from generic, non-actionable feedback, limiting behavioral impact. Method: We propose an LLM-driven personalized virtual nudge framework that integrates real-time usage data with large language models to generate context-aware, interpretable, and actionable water- and energy-saving recommendations. Using randomized controlled trials, causal forests, and structural equation modeling, we identify a novel psychological mechanism: enhanced self-efficacy, strengthened outcome expectations, and reduced reliance on social norms—collectively fostering intrinsic motivation. Results: The LLM-based nudge increased conservation intention by 18.0%, outperforming conventional statistical nudges by 88.6%; achieved high coverage (86.9%–98.0%); and significantly improved key psychological mediators. This work establishes the first paradigm for deep integration of LLMs into behavioral nudge design, offering a scalable, interpretable, and theoretically grounded technical pathway for sustainable behavior intervention.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• 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
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

The increasing amount of pressure related to water and energy shortages has increased the urgency of cultivating individual conservation behaviors. While the concept of nudging, i.e., providing usage-based feedback, has shown promise in encouraging conservation behaviors, its efficacy is often constrained by the lack of targeted and actionable content. This study investigates the impact of the use of large language models (LLMs) to provide tailored conservation suggestions for conservation intentions and their rationale. Through a survey experiment with 1,515 university participants, we compare three virtual nudging scenarios: no nudging, traditional nudging with usage statistics, and LLM-powered nudging with usage statistics and personalized conservation suggestions. The results of statistical analyses and causal forest modeling reveal that nudging led to an increase in conservation intentions among 86.9%-98.0% of the participants. LLM-powered nudging achieved a maximum increase of 18.0% in conservation intentions, surpassing traditional nudging by 88.6%. Furthermore, structural equation modeling results reveal that exposure to LLM-powered nudges enhances self-efficacy and outcome expectations while diminishing dependence on social norms, thereby increasing intrinsic motivation to conserve. These findings highlight the transformative potential of LLMs in promoting individual water and energy conservation, representing a new frontier in the design of sustainable behavioral interventions and resource management.

Problem

• Promoting daily water and energy conservation behaviors
• Enhancing efficacy of nudging with targeted, actionable content
• Using LLMs to provide personalized conservation suggestions

Innovation

• LLM-powered nudging with personalized suggestions
• Survey experiment with 1,515 university participants
• Causal forest modeling for conservation impact analysis