From Codebooks to VLMs: Evaluating Automated Visual Discourse Analysis for Climate Change on Social Media
Social media platforms have become primary arenas for climate communication, generating millions of images and posts that - if systematically analysed - can reveal which communication strategies mobilise public concern and which fall flat. We aim to facilitate such research by analysing how computer vision methods can be used for social media discourse analysis. This analysis includes application-based taxonomy design, model selection, prompt engineering, and validation. We benchmark six promptable vision-language models and 15 zero-shot CLIP-like models on two datasets from X (formerly Twitter) - a 1,038-image expert-annotated set and a larger corpus of over 1.2 million images, with 50,000 labels manually validated - spanning five annotation dimensions: animal content, climate change consequences, climate action, image setting, and image type. Among the models benchmarked, Gemini-3.1-flash-lite outperforms all others across all super-categories and both datasets, while the gap to open-weight models of moderate size remains relatively small. Beyond instance-level metrics, we advocate for distributional evaluation: VLM predictions can reliably recover population level trends even when per-image accuracy is moderate, making them a viable starting point for discourse analysis at scale. We find that chain-of-thought reasoning reduces rather than improves performance, and that annotation dimension specific prompt design improves performance. We release tweet IDs and labels along with our code at https://github.com/KathPra/Codebooks2VLMs.git.
Code (0)
등록된 구현이 없습니다.
Tasks
Prompt EngineeringSimilar Papers 제목 키워드 기반
When Discourse Pressures Conflict: Information Structure in Vision-Language Model Outputs
Vision-language models (VLMs) are increasingly evaluated for whether they identify the right visual content, but little is known about whether they express such content in a discourse-appropriate form. We address this re…
Question AnsweringClimateVID -- Social Media Videos Analysis and Challenges Involved
The pervasive growth of digital content, specifically short videos on social media platforms, has significantly altered how topics are discussed and understood in public discourse. In this work, we advance automated visu…
Zero-Shot Image ClassificationRight this way: Can VLMs Guide Us to See More to Answer Questions?
In question-answering scenarios, humans can assess whether the available information is sufficient and seek additional information if necessary, rather than providing a forced answer. In contrast, Vision Language Models …
Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)V$^2$R-Bench: Holistically Evaluating LVLM Robustness to Fundamental Visual Variations
Large Vision Language Models (LVLMs) excel in various vision-language tasks. Yet, their robustness to visual variations in position, scale, orientation, and context that objects in natural scenes inevitably exhibit due t…
Dataset GenerationObject RecognitionPositionLevel Up Your Tutorials: VLMs for Game Tutorials Quality Assessment
Designing effective game tutorials is crucial for a smooth learning curve for new players, especially in games with many rules and complex core mechanics. Evaluating the effectiveness of these tutorials usually requires …