MétaCan
Menu
Back to cohort
Record W4415707567 · doi:10.1109/tcss.2025.3608636

Detecting the Presence of COVID-19 Vaccination Hesitancy From South African Twitter Data Using Machine Learning

2025· article· W4415707567 on OpenAlexaff
Nicholas Perikli, Srimoy Bhattacharya, Blessing Ogbuokiri, Zahra Movahedi Nia, Benjamin Lieberman, Nidhi Tripathi, S. Dahbi, Finn Stevenson, Nicola Luigi Bragazzi, Jude Dzevela Kong, B. R. Mellado Garcia

Bibliographic record

VenueIEEE Transactions on Computational Social Systems · 2025
Typearticle
Language
FieldSocial Sciences
TopicVaccine Coverage and Hesitancy
Canadian institutionsYork University
FundersStyrelsen för Internationellt Utvecklingssamarbete
KeywordsSocial mediaLatent Dirichlet allocationSupport vector machinePreprocessorMicrobloggingSentiment analysisTopic modelData pre-processing

Abstract

fetched live from OpenAlex

Very few social media studies have been done on South African user-generated content during the COVID-19 pandemic and even fewer using hand-labeling over automated methods. Vaccination is a major tool in the fight against the pandemic, but vaccine hesitancy jeopardizes any public health effort. In this study, sentiment analysis on South African tweets related to vaccine hesitancy was performed, with the aim of training AI-mediated classification models and assessing their reliability in categorizing user-generated content. A dataset of 30,000 tweets from South Africa was extracted and hand-labeled into one of three sentiment classes—positive, negative, and neutral. The machine learning models used were long short-term memory (LSTM), bi-LSTM, support vector machine (SVM), bidirectional encoder representations from transformers (BERT)-base-cased and the RoBERTa-base models, whereby their hyperparameters were carefully chosen and tuned using the WandB platform. We used two different approaches when we preprocessed our data for comparison—one was a semantics-based method, while the other was a corpus-based method. The preprocessing of the tweets in our dataset was performed using both of these two different methods, respectively. All models were found to have low F1-scores within the range of 45%–55%, except for BERT and RoBERTa, which both achieved significantly better measures with overall F1-scores of 60% and 61%, respectively. Topic modeling using a latent Dirichlet allocation (LDA) was then performed on both the correctly classified and misclassified tweets of the RoBERTa model to gain insight on how to further improve the accuracy of these models.

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 imitation

Not 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.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.927
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.002
Science and technology studies0.0050.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.080
GPT teacher head0.346
Teacher spread0.266 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueIEEE Transactions on Computational Social SystemsSame topicVaccine Coverage and HesitancyFrench-language works237,207