| Abstract | During wildfires, users share real-time updates, warnings, and personal experiences on social media, which offers valuable insights for emergency response and disaster management. However, the vast volume and unstructured nature of social media data pose challenges in effectively extracting meaningful information. The first Canadian-specific multimodal dataset for wildfire-related social media analysis, WildFireCan-MMD, was recently introduced, and a multimodal classifier was developed to classify social media posts into thirteen categories. In this study, we collect 46,279 posts from X, posted during the wildfire seasons (May–October) of 2018 to 2024, and label them using the trained classifier. We then analyze trends in wildfire-related discussions over seven years. Our findings reveal seasonal patterns in public discourse, with significant spike linked to heightened concerns over smoke and air quality. Analysis of wildfire season over a year uncovered a sequential progression in social media discussions: an initial rise in reports of firefighting efforts was followed by increased posts about evacuations and emergency updates, with a delayed peak in smoke and air quality concerns as wildfire smoke spread. These insights show how social media captures the dynamic nature of wildfire events, reflecting public awareness and response as disasters unfold. Our study demonstrates the value of automated classification in extracting actionable intelligence from large-scale social media data. |
|---|
