ClassiVax

Classify vaccine-related news headlines into topic categories using a Recognizing Textual Entailment (RTE) approach, powered by the LuizNeves/BERT-NLI-vaccine-v2 model.

Built on the method described in:

Neves, L. F. F., Camargo, C. Q., & Massarani, L. (2025). Boosting Transformers: Recognizing Textual Entailment for Classification of Vaccine News Coverage. Computational Communication Research, 7(1), 1–32. https://doi.org/10.5117/CCR2025.1.1.NEVE

Installation

pip install classivax

Usage

Default classes (10 vaccine-related topics from the paper)

from classivax import ClassiVaxClassifier

clf = ClassiVaxClassifier()

result = clf.classify("Twitter will begin removing vaccine misinformation")
print(result["class"])   # "Vaccine Hesitancy and Mis-/Disinformation"
print(result["score"])   # e.g. 0.999

Note: if the text does not clearly match any of the provided classes (i.e., none of them achieve the entailment label), result["class"] and result["score"] will be None. Always check for this case rather than assuming a class is always returned:

result = clf.classify("some unrelated text")
if result["class"] is None:
    print("No class matched this text.")
else:
    print(result["class"], result["score"])

Batch classification

headlines = [
    "Twitter will begin removing vaccine misinformation",
    "Britain begins coronavirus vaccine rollout",
    "COVID-19 vaccination key to economic recovery",
]

df = clf.classify_batch(headlines)
print(df)

Custom classes

The underlying RTE approach also supports classifying text against any set of natural-language class descriptions you define — not just the original 10 classes.

custom_classes = {
    "Vaccine Safety Debate": "The headline discusses concerns, controversies, or debates about vaccine safety",
    "Vaccine Logistics": "The headline discusses shipping, storage, cold chain, or distribution logistics for vaccines",
}

clf = ClassiVaxClassifier(classes=custom_classes)
result = clf.classify("Cold storage shortages delay vaccine shipments to rural areas")
print(result["class"])  # "Vaccine Logistics"

Note: the underlying model was fine-tuned specifically on English-language, vaccine-related headlines from 2020–2021. Using custom classes outside this domain is supported, but accuracy has not been formally evaluated beyond the original study's scope — treat results on very different domains with appropriate caution.

The 10 default classes

How it works

For each headline, the classifier tests it against every class description as a text-hypothesis pair, following the entailment framework: the headline is the text (T), and each class description is a candidate hypothesis (H). The class whose description achieves the highest entailment score is selected as the prediction.

Troubleshooting

ImportError: cannot import name 'pipeline' from 'transformers'

If you see this error, especially in an Anaconda environment, it is usually not actually about transformers — it is caused by outdated or mismatched versions of Pillow and/or torchvision already installed in that environment, which transformers imports internally even for text-only tasks like this one.

To check, run:

import transformers
transformers.pipeline

and read the full traceback (not just the last line). Common underlying errors:

• AttributeError: module 'PIL.Image' has no attribute 'Resampling' → your Pillow is too old. Fix with:

  pip install --upgrade Pillow
  

• AttributeError: NEAREST_EXACT (or a similar torchvision.transforms.InterpolationMode error) → your torchvision is out of sync with transformers/torch. Since classivax only performs text classification, the simplest fix is to remove torchvision entirely:

  pip uninstall torchvision -y
  

  transformers will detect that torchvision is unavailable and skip the image-processing code path that causes the conflict.

After either fix, restart your Python kernel/interpreter before importing classivax again — a partially-loaded transformers module will not resolve itself without a restart.

Jupyter notebook can't find the package after pip install classivax

If you installed classivax inside a virtual environment but your notebook still fails to import it, your notebook is likely running a different Python kernel (e.g., a base Anaconda installation) than the one where you ran pip install. Register your environment as a Jupyter kernel:

pip install ipykernel
python -m ipykernel install --user --name=myenv --display-name "Python (myenv)"

Then, in Jupyter, go to Kernel → Change kernel and select the newly registered environment.

Citation

If you use this library or the underlying model in your research, please cite:

@article{neves2025boosting,
  title={Boosting Transformers: Recognizing Textual Entailment for Classification of Vaccine News Coverage},
  author={Neves, Luiz F. F. and Camargo, Chico Q. and Massarani, Luisa},
  journal={Computational Communication Research},
  volume={7},
  number={1},
  pages={1--32},
  year={2025},
  doi={10.5117/CCR2025.1.1.NEVE}
}

License

MIT