Sentiment Analysis on COVID-19-Related Social Distancing in Canada Using Twitter Data
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
BACKGROUND: COVID-19 preventive measures have been an obstacle to millions of people around the world, influencing not only their normal day-to-day activities but also affecting their mental health. Social distancing is one such preventive measure. People express their opinions freely through social media platforms like Twitter, which can be shared among other users. The articulated texts from Twitter can be analyzed to find the sentiments of the public concerning social distancing. OBJECTIVE: To understand and analyze public sentiments towards social distancing as articulated in Twitter textual data. METHODS: Twitter data specific to Canada and texts comprising social distancing keywords were extrapolated, followed by utilizing the SentiStrength tool to extricate sentiment polarity of tweet texts. Thereafter, the support vector machine (SVM) algorithm was employed for sentiment classification. Evaluation of performance was measured with a confusion matrix, precision, recall, and F1 measure. RESULTS: This study resulted in the extraction of a total of 629 tweet texts, of which, 40% of tweets exhibited neutral sentiments, followed by 35% of tweets showed negative sentiments and only 25% of tweets expressed positive sentiments towards social distancing. The SVM algorithm was applied by dissecting the dataset into 80% training and 20% testing data. Performance evaluation resulted in an accuracy of 71%. Upon using tweet texts with only positive and negative sentiment polarity, the accuracy increased to 81%. It was observed that reducing test data by 10% increased the accuracy to 87%. CONCLUSION: Results showed that an increase in training data increased the performance of the algorithm.
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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| 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