Factors Driving the Popularity and Virality of COVID-19 Vaccine Discourse on Twitter: Text Mining and Data Visualization Study
Bibliographic record
Abstract
BACKGROUND: COVID-19 vaccination is considered a critical prevention measure to help end the pandemic. Social media platforms such as Twitter have played an important role in the public discussion about COVID-19 vaccines. OBJECTIVE: The aim of this study was to investigate message-level drivers of the popularity and virality of tweets about COVID-19 vaccines using machine-based text-mining techniques. We further aimed to examine the topic communities of the most liked and most retweeted tweets using network analysis and visualization. METHODS: We collected US-based English-language public tweets about COVID-19 vaccines from January 1, 2020, to April 30, 2021 (N=501,531). Topic modeling and sentiment analysis were used to identify latent topics and valence, which together with autoextracted information about media presence, linguistic features, and account verification were used in regression models to predict likes and retweets. Among the 2500 most liked tweets and 2500 most retweeted tweets, network analysis and visualization were used to detect topic communities and present the relationship between the topics and the tweets. RESULTS: Topic modeling yielded 12 topics. The regression analyses showed that 8 topics positively predicted likes and 7 topics positively predicted retweets, among which the topic of vaccine development and people's views and that of vaccine efficacy and rollout had relatively larger effects. Network analysis and visualization revealed that the 2500 most liked and most retweeted retweets clustered around the topics of vaccine access, vaccine efficacy and rollout, vaccine development and people's views, and vaccination status. The overall valence of the tweets was positive. Positive valence increased likes, but valence did not affect retweets. Media (photo, video, gif) presence and account verification increased likes and retweets. Linguistic features had mixed effects on likes and retweets. CONCLUSIONS: This study suggests the public interest in and demand for information about vaccine development and people's views, and about vaccine efficacy and rollout. These topics, along with the use of media and verified accounts, have enhanced the popularity and virality of tweets. These topics could be addressed in vaccine campaigns to help the diffusion of content on Twitter.
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 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 | 0.003 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".