Eternagram: Inspiring Climate Action Through LLM-based Conversational Exploration of a Post-Devastation Climate Future
Suifang Zhou, Ray LC
TL;DR
Climate action messaging is often perceived as distant; this work uses a social-media-like, LLM-driven narrative in a speculative post-climate world to immerse users and motivate action. The approach combines a memory-enabled NPC (Ryno), a narrative corpus, and a GPT-powered interface with Stable Diffusion visuals, delivered through online and physical installations. It reports correlations between in-game perceptions and climate-awareness metrics, suggesting potential for increased pro-environmental intention. The installation design offers a scalable blueprint for engaging diverse publics through interactive storytelling that ties personal dialogue to real-world climate behaviors.
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.
