Analyzing COVID-19 Tweets using Health Behaviour Theories and Machine Learning
Bibliographic record
Abstract
In order to explain people's health habits, Health Behaviour Theories have been used to analyze posts on social media during previous incidents. Regarding the COVID-19 pandemic, social media data can expose public attitudes and experiences, as well as reveal elements that impede or encourage attempts to reduce the spread of the disease. This paper aims to use Health Behaviour Theories (Health Belief Model, Social Norm, and Trust) and Machine Learning to investigate or examine people's behaviours and reactions toward COVID-19. First, we extract COVID-19 comments on Twitter and use candidate keyphrases representing each health behaviour construct to label the comments. Next, we develop three machine learning models/classifiers - Support Vector Machine (SVM), Decision Tree (DT) and Logistic Regression (LR) - to automatically classify comments into appropriate constructs. We train and evaluate the models using 10-fold cross-validation and compare their performance based on precision, recall, and Fl-score metrics. Our results show that DT and SVM perform best with an overall Fl-score of up to 98% for multiclass (single label) classification, while DT outperform other classifiers with an overall Fl-score of up to 100% for multiclass-multilabel classification. Finally, we conduct thematic analysis of the comments in each construct to identify meaningful themes that represent key issues related to the COVID-19 pandemic. Our findings reveal 31 themes across all constructs.
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 | 0.003 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.004 | 0.003 |
| 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 | 0.001 |
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".