Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

OceanChat: The Effect of Virtual Conversational AI Agents on Sustainable Attitude and Behavior Change

Pat Pataranutaporn, Alexander Doudkin, Pattie Maes

TL;DR

OceanChat, an interactive system leveraging large language models to create conversational AI agents represented as animated marine creatures designed to promote environmental behavior and foster awareness through personalized dialogue, demonstrates how interactive narratives can bridge the gap between environmental knowledge and real-world behavior change.

Abstract

Marine ecosystems face unprecedented threats from climate change and plastic pollution, yet traditional environmental education often struggles to translate awareness into sustained behavioral change. This paper presents OceanChat, an interactive system leveraging large language models to create conversational AI agents represented as animated marine creatures -- specifically a beluga whale, a jellyfish, and a seahorse -- designed to promote environmental behavior (PEB) and foster awareness through personalized dialogue. Through a between-subjects experiment (N=900), we compared three conditions: (1) Static Scientific Information, providing conventional environmental education through text and images; (2) Static Character Narrative, featuring first-person storytelling from 3D-rendered marine creatures; and (3) Conversational Character Narrative, enabling real-time dialogue with AI-powered marine characters. Our analysis revealed that the Conversational Character Narrative condition significantly increased behavioral intentions and sustainable choice preferences compared to static approaches. The beluga whale character demonstrated consistently stronger emotional engagement across multiple measures, including perceived anthropomorphism and empathy. However, impacts on deeper measures like climate policy support and psychological distance were limited, highlighting the complexity of shifting entrenched beliefs. Our work extends research on sustainability interfaces facilitating PEB and offers design principles for creating emotionally resonant, context-aware AI characters. By balancing anthropomorphism with species authenticity, OceanChat demonstrates how interactive narratives can bridge the gap between environmental knowledge and real-world behavior change.

OceanChat: The Effect of Virtual Conversational AI Agents on Sustainable Attitude and Behavior Change

TL;DR

OceanChat, an interactive system leveraging large language models to create conversational AI agents represented as animated marine creatures designed to promote environmental behavior and foster awareness through personalized dialogue, demonstrates how interactive narratives can bridge the gap between environmental knowledge and real-world behavior change.

Abstract

Marine ecosystems face unprecedented threats from climate change and plastic pollution, yet traditional environmental education often struggles to translate awareness into sustained behavioral change. This paper presents OceanChat, an interactive system leveraging large language models to create conversational AI agents represented as animated marine creatures -- specifically a beluga whale, a jellyfish, and a seahorse -- designed to promote environmental behavior (PEB) and foster awareness through personalized dialogue. Through a between-subjects experiment (N=900), we compared three conditions: (1) Static Scientific Information, providing conventional environmental education through text and images; (2) Static Character Narrative, featuring first-person storytelling from 3D-rendered marine creatures; and (3) Conversational Character Narrative, enabling real-time dialogue with AI-powered marine characters. Our analysis revealed that the Conversational Character Narrative condition significantly increased behavioral intentions and sustainable choice preferences compared to static approaches. The beluga whale character demonstrated consistently stronger emotional engagement across multiple measures, including perceived anthropomorphism and empathy. However, impacts on deeper measures like climate policy support and psychological distance were limited, highlighting the complexity of shifting entrenched beliefs. Our work extends research on sustainability interfaces facilitating PEB and offers design principles for creating emotionally resonant, context-aware AI characters. By balancing anthropomorphism with species authenticity, OceanChat demonstrates how interactive narratives can bridge the gap between environmental knowledge and real-world behavior change.

Paper Structure

This paper contains 39 sections, 1 equation, 17 figures, 2 tables.

Table of Contents

  1. Safe and Responsible Innovation Statement
  2. Introduction
  3. Related Work
  4. LLMs and Persuasive Interactions for Sustainability
  5. Methodological Considerations: Real and Synthetic Participants
  6. Methodology
  7. Study Design
  8. Chatbot Design
  9. Behavioral Design
  10. Technical Implementation
  11. Ethical Considerations
  12. Sample Size
  13. Participant Recruitment
  14. Statistical Analysis and Model Specification
  15. Dependent Variables
  16. ...and 24 more sections

Figures (17)

  • Figure 1: Study Design Overview
  • Figure 2: Overview of all three conditions for the seahorse character (top) and OceanChat interfaces of all three animals (bottom)
  • Figure 3: Excerpt of Post-Intervention Product Shopping Scenario (Sustainable Choice Preferences)
  • Figure 4: Comparison of synthetic and real participant results for the dependent variable "Sustainable Consumption".
  • Figure 5: Regression analysis for animal conditions and perceived variables, showing coefficient and p-values
  • ...and 12 more figures