| --- |
| license: apache-2.0 |
| base_model: vinai/bartpho-syllable |
| tags: |
| - vietnamese |
| - spam-detection |
| - text-classification |
| - e-commerce |
| datasets: |
| - ViSpamReviews |
| metrics: |
| - accuracy |
| - macro-f1 |
| - macro-precision |
| - macro-recall |
| model-index: |
| - name: bartpho-spam-binary |
| results: |
| - task: |
| type: text-classification |
| name: Spam Review Detection |
| dataset: |
| name: ViSpamReviews |
| type: ViSpamReviews |
| metrics: |
| - type: accuracy |
| value: 0.8751 |
| - type: macro-f1 |
| value: 0.8358 |
| --- |
| # bartpho-spam-binary: Spam Review Detection for Vietnamese Text |
|
|
| This model is a fine-tuned version of [vinai/bartpho-syllable](https://huggingface.co/vinai/bartpho-syllable) on the **ViSpamReviews** dataset for spam review detection in Vietnamese e-commerce reviews. |
|
|
| ## Model Details |
|
|
| * **Base Model**: `vinai/bartpho-syllable` |
| * **Description**: BART Pho - Vietnamese BART model |
| * **Dataset**: ViSpamReviews (Vietnamese Spam Review Dataset) |
| * **Fine-tuning Framework**: HuggingFace Transformers |
| * **Task**: Spam Review Detection (binary) |
| * **Number of Classes**: 2 |
|
|
| ### Hyperparameters |
|
|
| * Max sequence length: `256` |
| * Learning rate: `5e-5` |
| * Batch size: `32` |
| * Epochs: `100` |
| * Early stopping patience: `5` |
|
|
| ## Dataset |
|
|
| The model was trained on the **ViSpamReviews** dataset, which contains 19,860 Vietnamese e-commerce review samples. The dataset includes: |
|
|
| * **Train set**: 14,299 samples (72%) |
| * **Validation set**: 1,590 samples (8%) |
| * **Test set**: 3,971 samples (20%) |
|
|
| ### Label Distribution |
|
|
|
|
| * **Non-spam** (0): Genuine product reviews |
| * **Spam** (1): Fake or promotional reviews |
|
|
| ## Results |
|
|
| The model was evaluated on the test set with the following metrics: |
|
|
| * **Accuracy**: `0.8751` |
| * **Macro-F1**: `0.8358` |
|
|
|
|
| ## Usage |
|
|
| You can use this model for spam review detection in Vietnamese text. Below is an example: |
|
|
| ```python |
| from transformers import AutoTokenizer, AutoModelForSequenceClassification |
| import torch |
| |
| # Load model and tokenizer |
| model_name = "visolex/bartpho-spam-binary" |
| tokenizer = AutoTokenizer.from_pretrained(model_name) |
| model = AutoModelForSequenceClassification.from_pretrained(model_name) |
| |
| # Example review text |
| text = "Sản phẩm này rất tốt, shop giao hàng nhanh!" |
| |
| # Tokenize |
| inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=256) |
| |
| # Predict |
| with torch.no_grad(): |
| outputs = model(**inputs) |
| predicted_class = outputs.logits.argmax(dim=-1).item() |
| probabilities = torch.softmax(outputs.logits, dim=-1) |
| |
| |
| # Map to label |
| label_map = {0: "Non-spam", 1: "Spam"} |
| predicted_label = label_map[predicted_class] |
| confidence = probabilities[0][predicted_class].item() |
| |
| print(f"Text: {text}") |
| print(f"Predicted: {predicted_label} (confidence: {confidence:.2%})") |
| |
| ``` |
|
|
| ## Citation |
|
|
| If you use this model, please cite: |
|
|
| ```bibtex |
| @misc{{ |
| {model_key}_spam_detection, |
| title={{{description}}}, |
| author={{ViSoLex Team}}, |
| year={{2025}}, |
| howpublished={{\url{{https://huggingface.co/{visolex/bartpho-spam-binary}}}}} |
| }} |
| ``` |
|
|
| ## License |
|
|
| This model is released under the Apache-2.0 license. |
|
|
| ## Acknowledgments |
|
|
| * Base model: [{base_model}](https://huggingface.co/{base_model}) |
| * Dataset: ViSpamReviews (Vietnamese Spam Review Dataset) |
| * ViSoLex Toolkit for Vietnamese NLP |
|
|
