LLMs analyze climate discourse across paid ads and social media

Researchers have developed a new method for analyzing online climate discourse by comparing paid advertising on platforms like Meta with organic discussions on social media, specifically Bluesky. This approach utilizes large language models to identify and label themes without requiring pre-defined topics. The study found that paid advertisements focus on promoting specific solutions in a formal tone, while organic posts emphasize systemic critiques with a scientifically grounded, crisis-oriented perspective. The framework is designed to be generalizable for comparative thematic analysis across different communication environments. AI

IMPACT This research provides a novel framework for analyzing and comparing online discourse across different platforms, potentially improving understanding of how climate change is communicated.

RANK_REASON The cluster contains an academic paper detailing a new methodology for analyzing online discourse using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• Bluesky
• Meta
• Tunazzina Islam

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →