Using Social Media to Model Community-Based Behavioral Response During Public Health Emergencies: A Case Study of the 2023 Canadian Wildfires
Bibliographic record
Abstract
New York City (NYC) experienced severe air pollution from Canadian wildfires in June 2023, disrupting travel and daily activities. This study analyzed public reactions to evacuation, indoor activities, shopping, and recreation using geotagged X posts during the air pollution crisis. Geotagged posts were reverse geocoded to census blocks and spatially joined with socioeconomic and demographic data from the U.S. census and American Community Survey. The dataset initially comprised 0.59 million geotagged X posts from 66,858 unique users in NYC over a 1-week period. After relevance filtering, the final dataset included 10,258 posts from 10,258 unique users on wildfire-related travel and activity discussions. Public reactions were analyzed using a BERT-based natural language processing model, whereas a gender–race model inferred users’ gender and racial identities based on their first and last names. A multinomial logit model assessed how socioeconomic and demographic factors influenced activity discussions during the crisis. The findings revealed demographic differences in responses. For instance, females were less likely to discuss evacuation and essential trips, possibly owing to continued workplace operations despite hazardous conditions. Racial differences were also evident, with Asians more frequently mentioning evacuation and commuting, whereas African Americans showed lower engagement in discussions about social and recreational activities. Socioeconomic disparities further influenced response patterns, as lower-income and less-educated groups expressed fewer concerns about evacuation, highlighting potential barriers to crisis awareness and preparedness. These insights emphasize the need for targeted communication strategies and equitable health interventions to ensure that emergency responses effectively reach vulnerable populations during environmental crises.
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 | 0.007 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| 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".