🤖 AI Summary
Environmental education faces challenges in motivating pro-environmental behavior due to the delayed and indirect consequences of individual actions. To address this, this study designs and empirically validates EcoEcho, a generative AI–driven ecological simulation game. EcoEcho innovatively integrates multimodal agents—capable of speech and text interaction—with real-time, visualized feedback of action–environment consequences, emphasizing behavioral intention intervention over attitude change. A mixed-methods evaluation (surveys, behavioral logs, interviews) with 23 participants demonstrates that the game significantly increases sustainable behavioral intention (p < 0.01), while yielding no statistically significant attitude shift—supporting its efficacy at the behavioral level. This work pioneers a closed-loop synergy between multimodal agent guidance and dynamic consequence feedback. It establishes a novel, empirically grounded paradigm for generative AI–enhanced environmental education centered on actionable behavioral intervention.
📝 Abstract
Unsustainable behaviors are challenging to prevent due to their long-term, often unclear consequences. Games offer a promising solution by creating artificial environments where players can immediately experience the outcomes of their actions. To explore this potential, we developed EcoEcho, a GenAI-powered game leveraging multimodal agents to raise sustainability awareness. These agents engage players in natural conversations, prompting them to take in-game actions that lead to visible environmental impacts. We evaluated EcoEcho using a mixed-methods approach with 23 participants. Results show a significant increase in intended sustainable behaviors post-game, although attitudes towards sustainability only slightly improved. This finding highlights the potential of multimodal agents and action-consequence mechanics to effectively motivate real-world behavioral changes such as raising environmental sustainability awareness.