CLAImate: AI-Enabled Climate Change Communication through Personalized and Localized Narrative Visualizations

2025-07-15

AI Summary

To address public comprehension deficits arising from abstract, technical climate communication, this study proposes an AI framework integrating personalized dialogue generation with geolocalized visualization. Methodologically, it pioneers the fusion of natural language generation (NLG) and geolocation technologies, augmented by FACTSCORE for factual consistency verification and the SNLI model for semantic entailment validation to ensure content credibility; risk information is spatially embodied via purpose-built visual design. The core contribution is a scalable “dialogue–visualization” co-design system that significantly enhances communicative relevance and user resonance while maintaining high accuracy—FACTSCORE of 70% and SNLI entailment accuracy of 66%. Expert evaluation confirms its effectiveness, and user studies show 70% of participants reported markedly improved understanding of localized climate risks, empirically validating the practical value of personalized, geolocalized interaction paradigms in climate communication.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

Communicating climate change remains challenging, as climate reports, though rich in data and visualizations, often feel too abstract or technical for the public. Although personalization can enhance communication, most tools still lack the narrative and visualization tailoring needed to connect with individual experiences. We present CLAImate, an AI-enabled prototype that personalizes conversation narratives and localizes visualizations based on users' climate knowledge and geographic location. We evaluated CLAImate through internal verification of factual correctness, a formative study with experts, and a pilot with UK residents. CLAImate achieved 66% SNLI accuracy and 70% FACTSCORE. Visualization experts appreciated its clarity and personalization, and seven out of ten UK participants reported better understanding and local relevance of climate risks with CLAImate. We also discuss design challenges in personalization, accuracy, and scalability, and outline future directions for integrating visualizations in personalized conversational interfaces.

Problem

• Addressing abstract climate communication for public understanding
• Lacking personalized narrative and visualization in climate tools
• Enhancing climate risk relevance through localized AI solutions

Innovation

• AI personalizes climate narratives and visualizations
• Localizes visualizations based on user location
• Achieves 66% SNLI and 70% FACTSCORE accuracy