Using COVID-19 Vaccine Attitudes Found in Tweets to Predict Vaccine Perceptions in Traditional Surveys: Infodemiology Study
Bibliographic record
Abstract
BACKGROUND: Traditionally, surveys are conducted to answer questions related to public health but can be costly to execute. However, the information that researchers aim to extract from surveys could potentially be retrieved from social media, which possesses data that are highly accessible and lower in cost to collect. OBJECTIVE: This study aims to evaluate whether attitudes toward COVID-19 vaccines collected from the Household Pulse Survey (HPS) could be predicted using attitudes extracted from Twitter (subsequently rebranded X). Ultimately, this study aimed to determine whether Twitter can provide us with similar information to that observed in traditional surveys or whether saving money comes at the cost of losing rich data. METHODS: COVID-19 vaccine attitudes were extracted from the HPS conducted between January 6 and May 25, 2021. Twitter's streaming application programming interface was used to collect COVID-19 vaccine tweets during the same period. A sentiment and emotion analysis of tweets was conducted to examine attitudes toward the COVID-19 vaccine on Twitter. Generalized linear models and generalized linear mixed models were used to evaluate the ability of COVID-19 vaccine attitudes on Twitter to predict vaccine attitudes in the HPS. RESULTS: The results revealed that vaccine perceptions expressed on Twitter performed well in predicting vaccine perceptions in the survey. CONCLUSIONS: These findings suggest that the information researchers aim to extract from surveys could potentially also be retrieved from a more accessible data source, such as Twitter. Leveraging Twitter data alongside traditional surveys can provide a more comprehensive and nuanced understanding of COVID-19 vaccine perceptions, facilitating evidence-based decision-making and tailored public health strategies.
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 | 0.007 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| 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 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".