Analysis of Canadian Wildfire Tweets Over Seven Years
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.005 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".