Covid-19 Sentiment Analysis on X (formerly Twitter) Using Machine Learning Classifiers: Performance Comparison and Key Insights
Bibliographic record
Abstract
The current generation and widely used platforms like X (formerly Twitter) enable the study of public attitudes toward important topics, including the COVID-19 outbreak. In this paper, machine learning approaches (ML) are employed to build a sentiment analysis system for COVID-19 hashtagged tweets. We employed four ML classifiers, namely Naïve Bayes (NB), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF), to classify the tweets into positive, negative, and neutral sentiments. In total, the examined dataset includes 178,240 tweets that are related to COVID-19 and were preprocessed through natural language processing. To assess the performance of the classifiers, we used accuracy, precision and recall, and F1 score. The results show that the DT classifier has the highest accuracy of 94% when compared to other models concerning precision and recall. Undersampling and oversampling were the techniques examined for addressing the issue of class imbalance. Such findings imply that ML, especially the SVM and DTs, can be useful in the next large-scale public sentiment analysis during a pandemic. Among the recommendations for further enhancements of the sentiment analysis approaches and their use in monitoring people’s reactions to social media during the pandemic are included in the paper.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 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 | 0.002 |
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".