Eternagram: Probing Player Attitudes in Alternate Climate Scenarios Through a ChatGPT-Driven Text Adventure

TL;DR

This paper presents a novel AI-driven game-based assessment using a GPT chatbot within a climate scenario game to better understand player attitudes towards climate change, capturing authentic opinions through immersive interaction.

Contribution

It introduces a new GPT-powered chatbot integrated into a climate scenario game to improve attitude assessment and identifies key personality traits influencing pro-climate attitudes.

Findings

Players' climate awareness aligns with in-game perceptions after gameplay.

Traits like Openness and Agreeableness predict pro-climate attitudes.

The method enhances naturalness and authenticity of attitude assessments.

Abstract

Conventional methods of assessing attitudes towards climate change are limited in capturing authentic opinions, primarily stemming from a lack of context-specific assessment strategies and an overreliance on simplistic surveys. Game-based Assessments (GBA) have demonstrated the ability to overcome these issues by immersing participants in engaging gameplay within carefully crafted, scenario-based environments. Concurrently, advancements in AI and Natural Language Processing (NLP) show promise in enhancing the gamified testing environment, achieving this by generating context-aware, human-like dialogues that contribute to a more natural and effective assessment. Our study introduces a new technique for probing climate change attitudes by actualizing a GPT-driven chatbot system in harmony with a game design depicting a futuristic climate scenario. The correlation analysis reveals an assimilation effect, where players' post-game climate awareness tends to align with their in-game perceptions. Key predictors of pro-climate attitudes are identified as traits like 'Openness' and 'Agreeableness', and a preference for democratic values.