Social Media Behaviour Analysis in Disaster-Response Messages of Floods and Heat Waves via Artificial Intelligence
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This paper analyses social media data in multiple disaster-related collections of floods and heat waves in the UK. The proposed method uses machine learning classifiers based on deep bidirectional neural networks trained on benchmark datasets of disaster responses and extreme events. The resulting models are applied to perform a qualitative analysis via topic inference in text data. We further analyse a set of behavioural indicators and match them with climate variables via decoding synoptical records to analyse thermal comfort. We highlight the advantages of aligning behavioural indicators along with climate variables to provide with 7 additional valuable information to be considered especially in different phases of a disaster and applicable to extreme weather periods. The positiveness of messages is around 8% for disaster, 1% for disaster and medical response, 7% for disaster and humanitarian related messages. This shows the reliability of such data for our case studies. We show the transferability of this approach to be applied to any social media data collection.
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.
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 | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.000 | 0.002 |
| 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 it