Downloads · 30 days
18
4% of all-time downloads
vzani/portuguese-fake-news-classifier-bertimbau-combined
portuguese-fake-news-classifier-bertimbau-combined is a text classification model from vzani. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
This repository contains fine-tuned versions of BERTimbau for the task of fake news detection in Portuguese. The models are trained and evaluated on corpora derived from Brazilian Portuguese dataset Fake.br combined w…
Downloads · 30 days
18
4% of all-time downloads
All-time downloads
431
Public
Parameters
109M
571 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors436 MB · 76%
From the Hugging Face model README
This repository contains fine-tuned versions of BERTimbau for the task of fake news detection in Portuguese. The models are trained and evaluated on corpora derived from Brazilian Portuguese dataset Fake.br combined with FakeTrue.Br.
pt)bertimbau-combined Fine-tuned using the combined dataset from Fake.br and FakeTrue.Br.
bertimbau-fake-br Fine-tuned using the Fake.br dataset from Fake.br.
bertimbau-faketrue-br Fine-tuned using the FakeTrue.Br dataset from FakeTrue.Br.
Each variant has its own confusion matrix, classification report, and predictions stored as artifacts.
{
"learning_rate": 3.1260711108007855e-05,
"batch_size": 16,
"epochs": 7,
"layers_to_freeze": 8, # Train the last 4 layers.
}
neuralmind/bert-base-portuguese-casedEvaluation metrics are stored in the repo Files and Versions section as:
confusion_matrix.pngfinal_classification_report.parquetfinal_predictions.parquetThese files provide per-class performance and prediction logs for reproducibility.
from transformers import (
AutoModelForSequenceClassification,
AutoTokenizer,
pipeline, # type: ignore
)
model_name = (
"vzani/portuguese-fake-news-classifier-bertimbau-combined" # or fake-br / faketrue-br
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
clf = pipeline("text-classification", model=model, tokenizer=tokenizer) # type: ignore
def predict(text: str) -> tuple[bool, float]:
result = clf(text)[0]
true_false = True if result["label"] == "LABEL_1" else False # noqa: SIM210
return true_false, result["score"]
if __name__ == "__main__":
text = "BOMBA! A Dilma vai taxar ainda mais os pobres!"
print(predict(text))
The expected output is a Tuple where the first entry represents the classification (True for true news and False for fake news) and the second the probability assigned to the predicted class (ranging from 0 to 1.0).
(False, 0.9999247789382935)
You can find the source code that produced this model in the repository below:
The source contains all the steps from data collection, evaluation, hyperparameter fine tuning, final model tuning and publishing to HuggingFace. If you use it, please remember to credit the author and/or cite the work.
@misc{zani2025portuguesefakenews,
author = {ZANI, Vinícius Augusto Tagliatti},
title = {Avaliação comparativa de técnicas de processamento de linguagem natural para a detecção de notícias falsas em Português},
year = {2025},
pages = {61},
address = {São Carlos},
school = {Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo},
type = {Trabalho de Conclusão de Curso (MBA em Inteligência Artificial e Big Data)},
note = {Orientador: Prof. Dr. Ivandre Paraboni}
}