Monitoring the well-being of vulnerable transit riders using machine learning based sentiment analysis and social media: Lessons from COVID-19
Bibliographic record
Abstract
Using open-source data, we show that despite significant reductions in global public transit during the COVID-19 pandemic, ∼20% of ridership continues during social distancing measures. Current urban transport data collection methods do not account for the distinct behavioural and psychological experiences of the population. Therefore, little is known about the travel experience of vulnerable citizens that continue to rely on public transit and their concerns over risk, safety and other stressors that could negatively affect their health and well-being. We develop a machine learning approach to augment conventional transport data collection methods by curating a population segmented Twitter dataset representing the travel experiences of ∼120,000 transit riders before and during the pandemic in Metro Vancouver, Canada. Results show a heightened increase in negative sentiments, differentiated by age, gender and ethnicity associated with public transit indicating signs of psychological stress among travellers during the first and second waves of COVID-19. Our results provide empirical evidence of existing inequalities and additional risks faced by citizens using public transit during the pandemic, and can help raise awareness of the differential risks faced by travellers. Our data collection methods can help inform more targeted social-distancing measures, public health announcements, and transit monitoring services during times of transport disruptions and closures.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".