# WildFireCan-MMD: A Multimodal Dataset for Classification of User-Generated Content During Wildfires in Canada

arXiv: https://arxiv.org/abs/2504.13231 · HTML: https://mlsanity.com/paper/2504.13231/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 80 references that are in the map.
- First posted on arXiv 17 Apr 2025.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [SmolVLM: Redefining small and efficient multimodal models](https://mlsanity.com/paper/2504.05299/) (2025)
- [CrisisMMD: Multimodal Twitter Datasets from Natural Disasters](https://mlsanity.com/paper/1805.00713/) (2018)
- [Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective](https://mlsanity.com/paper/2012.12305/) (2020)
- [HumAID: Human-Annotated Disaster Incidents Data from Twitter with Deep Learning Benchmarks](https://mlsanity.com/paper/2104.03090/) (2021)
- [Multimodal Categorization of Crisis Events in Social Media](https://mlsanity.com/paper/2004.04917/) (2020)
- [Vision-Language Intelligence: Tasks, Representation Learning, and Large Models](https://mlsanity.com/paper/2203.01922/) (2022)
- [CityLLaVA: Efficient Fine-Tuning for VLMs in City Scenario](https://mlsanity.com/paper/2405.03194/) (2024)
- [Analysis of Social Media Data using Multimodal Deep Learning for Disaster Response](https://mlsanity.com/paper/2004.11838/) (2020)
- [A social context-aware graph-based multimodal attentive learning framework for disaster content classification during emergencies: a benchmark dataset and method](https://mlsanity.com/paper/2410.08814/) (2024)
- [TBCOV: Two Billion Multilingual COVID-19 Tweets with Sentiment, Entity, Geo, and Gender Labels](https://mlsanity.com/paper/2110.03664/) (2021)
- [CrisisKAN: Knowledge-infused and Explainable Multimodal Attention Network for Crisis Event Classification](https://mlsanity.com/paper/2401.06194/) (2024)
- [Multilingual transformer and BERTopic for short text topic modeling: The case of Serbian](https://mlsanity.com/paper/2402.03067/) (2024)
- [Characterizing Communities of Hashtag Usage on Twitter During the 2020 COVID-19 Pandemic by Multi-view Clustering](https://mlsanity.com/paper/2008.01139/) (2020)
- [The crime of being poor](https://mlsanity.com/paper/2303.14128/) (2023)
- [Social Media Information Sharing for Natural Disaster Response](https://mlsanity.com/paper/2005.07019/) (2020)

## Abstract (arXiv)

Rapid information access is vital during wildfires, yet traditional data sources are slow and costly. Social media offers real-time updates, but extracting relevant insights remains a challenge. In this work, we focus on multimodal wildfire social media data, which, although existing in current datasets, is currently underrepresented in Canadian contexts. We present WildFireCan-MMD, a new multimodal dataset of X posts from recent Canadian wildfires, annotated across twelve key themes. We evaluate zero-shot vision-language models on this dataset and compare their results with those of custom-trained and baseline classifiers. We show that while baseline methods and zero-shot prompting offer quick deployment, custom-trained models outperform them when labelled data is available. Our best-performing custom model reaches 84.48% f-score, outperforming VLMs and baseline classifiers. We also demonstrate how this model can be used to uncover trends during wildfires, through the collection and analysis of a large unlabeled dataset. Our dataset facilitates future research in wildfire response, and our findings highlight the importance of tailored datasets and task-specific training. Importantly, such datasets should be localized, as disaster response requirements vary across regions and contexts.