license: mit
language:
- en
base_model:
- google-bert/bert-base-uncased
Anti-Vax-Misinfo-Detector is a simple vaccine misinformation detector fine-tuned on tweets.
The Anti-Vax-Misinfo-Detector is a fine-tuned version of the "bert-base-uncased" transformer model and inspired by the "COVID-19 Misinformation Detector", found here. It is fine-tuned on a dataset containing tweets relating to the COVID-19 pandemic; each tweet is labelled as containing misinformation (1) or not (0), as verified by healthcare experts. The dataset used is:
ANTi-Vax: a novel Twitter dataset for COVID-19 vaccine misinformation detection
For detailed information on the fine-tuning, please check out the attached Jupyter notebook "Bert_CovidVaccine_Misinformation.ipynb." More information can also be found in the related paper Disagreement as a way to study misinformation and its effects.