Vision-language models effectively analyze climate change discourse on social media

Researchers have developed and evaluated automated visual discourse analysis techniques for climate change communication on social media. They benchmarked various vision-language models (VLMs) and CLIP-like models on datasets derived from X (formerly Twitter), analyzing image content across categories like climate consequences and actions. The study found that Gemini-3.1-flash-lite performed best, and that distributional evaluation is crucial for large-scale discourse analysis, even with moderate per-image accuracy. AI

影响 VLMs can reliably recover population-level trends in social media discourse, enabling large-scale analysis of climate communication strategies.

排序理由 Academic paper evaluating vision-language models for social media discourse analysis.

在 arXiv cs.CV 阅读 →

• Gemini-3.1-flash-lite
• Katharina Prasse
• X

• 论文
• 产品

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →