Eternagram: Inspiring Climate Action Through LLM-based Conversational Exploration of a Post-Devastation Climate Future

2025-07-07

International Conference on Conversational User Interfaces

AI Summary

This work proposes a large language model (LLM)-driven text-based adventure game designed to bridge the gap between public perception and climate action by situating players in a post-climate-disaster alien world. Through interactive dialogues with AI-generated characters and image-based narratives, players engage with metaphorical scenarios that prompt reflection on real-world environmental behaviors. The approach innovatively integrates LLM-powered storytelling, social media–inspired interaction patterns, and visual narrative techniques to foster emotional resonance and motivate pro-environmental intentions. An empirical deployment at the CHI conference demonstrated that participants exhibited significantly heightened identification with climate action after the experience, underscoring the efficacy and potential of generative AI as a tool for intervention in socio-environmental discourse.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

Climate action is difficult to persuade because we tend to perceive climate change as remote and disconnected from daily life. Instead of traditional informational engagements, game-based interventions can create narratives that immerse the visitor in situations where their actions have tangible consequences. To make these narratives engaging, we used a speculative scenario of an alien stumbling upon social media to obliquely address climate change through a text-based adventure game installation. Mimicking visitors’ natural dialogue in social media apps, we designed an LLM-based chatbot with knowledge of post-climate devastated world that mirrors our own planet Earth. In discovering the world’s downfall through interactive chatting and posted images, players begin to realize that their own actions can make a difference on impacts of climate change in this distant world, fostering pro-environmental attitudes. Previously published at CHI, this game installation demonstrates the potential of LLM-based creative narratives in exploring speculative worlds driving social change.

Problem

• climate action
• climate change
• public engagement
• pro-environmental behavior
• speculative narrative

Innovation

• LLM-based chatbot
• speculative design
• climate action
• game-based intervention
• conversational narrative