Table of Contents
Fetching ...

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.

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

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.
Paper Structure (13 sections, 4 figures)

This paper contains 13 sections, 4 figures.

Figures (4)

  • Figure 1: Example game flow for the interactive form. (Top) How players can trigger the GenAI agent to go from one place to another in the conversation as they explore the world through natural conversation. (Bottom) The way the full game flow works in the interactive online version. Players can stop at any point but have the option to explore the entire story by making it to the final scene.
  • Figure 2: The in-game interface emulates the original design of Instagram's UI
  • Figure 3: Narrative engendered by the conversation-based interaction shown as GenAI-created images. Through interactive dialogue with the stranger, the player uncovers (Left) a once-thriving, once advanced civilization that has now fallen into ruin (Right) as described by the LLM-based chatbot character due to a sequence of events leading to catastrophic climate change.
  • Figure 4: Floor plan and layout for a potential physical installation, including 3D view with setup needed (Left) and detailed specs and measurements recommended (Right).