Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Suifang Zhou, Latisha Besariani Hendra, Qinshi Zhang, Jussi Holopainen, RAY LC

TL;DR

This 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, and reveals an assimilation effect, where players' post-game climate awareness tends to align with their in-game perceptions.

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.

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

TL;DR

This 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, and reveals an assimilation effect, where players' post-game climate awareness tends to align with their in-game perceptions.

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.
Paper Structure (33 sections, 5 figures, 4 tables)

This paper contains 33 sections, 5 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Climate Change Attitude Assessment
  4. Serious Game as Assessment Tool
  5. GPT-based Chatbot Systems and AI-Generated Content
  6. Game Design Approach
  7. Key Challenges
  8. World Building as Corpus
  9. Main Framework
  10. Narrative Outline Walkthrough
  11. In-game Question Item Design
  12. Character Design: Ryno
  13. Prompt Engineering
  14. Game Interface Design
  15. Methods
  16. ...and 18 more sections

Figures (5)

  • Figure 1: Player-Ryno Interaction: Conversation flow during player-Ryno Interaction across different trigger states
  • Figure 2: Illustration of compatible game loop design integrating player-GPT interaction
  • Figure 3: The in-game interface emulates the original design of Instagram's UI
  • Figure 4: Summary of the research protocol during three distinct periods. Prior to commencing gaming, users are required to fill out a pre-survey that covers demographic information, political perspectives and involvement, as well as climate sentiments. While playing, players participate in an in-game survey that specifically examines their climate opinions and objectives. Following the games, a post-survey is administered that is similar to the pre-survey, with the exception of demographic questions. The purpose of this survey is to evaluate any changes in attitudes or intentions.
  • Figure 5: Scatter plots correlating in-game climate attitudes with pre- and post-gameplay assessments. The left plot shows attitudes before gameplay, and the right plot shows attitudes after gameplay, both compared to in-game attitudes. The least squares fit line in both indicates a positive correlation.