from transformers import AutoTokenizer, AutoModelForSequenceClassification

# Load model and tokenizer
model_name = "Qiegu/fake-review-detection-bert"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# Classify a review
text = "This product is amazing! I love it so much!"
inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
outputs = model(**inputs)
prediction = outputs.logits.argmax(dim=1).item()

# 0 = Real review, 1 = Fake review
result = "Fake" if prediction == 1 else "Real"
print(f"Review classification: {result}")

Model Performance

Accuracy: Trained on diverse product review datasets
Use Case: E-commerce review authenticity detection
Input: Product review text
Output: Binary classification (Real/Fake)

Citation

If you use this model in your research, please cite:

bibtex

@misc{fake-review-detection-bert,
  title={Fake Review Detection BERT Model},
  author={Your Name},
  year={2024},
  publisher={Hugging Face},
  url={https://huggingface.co/Qiegu/fake-review-detection-bert}
}