Mining Geotagged Tweets: Tracking Spatiotemporal Variation of Mental Health in Canada during COVID-19 Pandemic
Bibliographic record
Abstract
This thesis explores and analyzes the evolution of the pandemic as a stressor on mental health in Canada through monitoring the sentiment polarity dynamics, emotion trends, and changes in keywords being discussed on Twitter, spanning between January 2020 to December 2022. Leveraging the surging amount of geotagged social media data, this study deploys a combination of machine learning, geospatial mapping, and social sensing as a new approach to observe, quantify and evaluate the evolution of national-wide emotion trends and psychological status along the COVID-19 pandemic timeline in Canada, interpret the underlying key factors and events, and thus inform us on how to mentally “re-start” in the post-pandemic era. The proposed methods include social sensing, large-scale sentiment polarity detection, emotion classification, keyword analysis, and kernel density mapping. The dataset after processing is consisting of 430,399 geo-tagged tweets discussing pandemic subjects posted by Canadian users from January 1, 2020 to December 31, 2022. \n \nThe results of this study reveal that the overall sentiment and emotion composition was the most optimistic during the early half of the pandemic, from the early spring of 2020 to the summer of 2021, and turned to decline from then to the end of 2022, sending a warning signal in public mental well-being. Beneath this trend, several driving events emerged, ranging from the declaration of state of emergency in March 2020, the peak of vaccine hesitancy in November 2020, the release of new vaccine mandate in January 2022 to the Freedom Convey lasting from January 2022 to February 2022. The results also indicate that there is an observable geospatial disparity in the shifting patterns and the overall mental health levels between Montréal, a French-dominant region, and Vancouver, Calgary, Edmonton, Toronto, and Ottawa-Gatineau, which are English-dominant or bilingual regions. Also, along with a delayed period of peaks and bottoms in sentiment polarity, Toronto is displaying a slightly different mood than the other English-speaking cities. Last but not the least, we propose two action strategies, promoting education on the importance of vaccine behaviours and rebalancing the COVID-19 restrictions, for boosting public confidence regarding the pandemic and rebuilding psychological resilience in the current post-pandemic era. \n \nAs the first work tracking the long-term mental health of Canada as a country during the pandemic, this study evidences the conclusion that as the global economy starts to recover and the number of cases becomes gradually under control with the availability of the vaccine, the public psychological condition is not lifting as fast as the economy and the physical health in today’s post-pandemic world.
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 | 0.000 | 0.002 |
| 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 | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 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".