README.md

---
license: mit
base_model: bert-base-multilingual-cased
tags:
- vietnamese
- hate-speech-detection
- text-classification
- offensive-language-detection
datasets:
- visolex/vihsd
metrics:
- accuracy
- macro-f1
- weighted-f1
model-index:
- name: mbert-hsd
  results:
  - task:
      type: text-classification
      name: Hate Speech Detection
    dataset:
      name: ViHSD
      type: hate-speech-detection
    metrics:
    - type: accuracy
      value: 0.9360
    - type: macro-f1
      value: 0.8044
    - type: weighted-f1
      value: 0.9317
    - type: macro-precision
      value: 0.8850
    - type: macro-recall
      value: 0.7518
---

# mBERT: Hate Speech Detection for Vietnamese Text

This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) 
on the **ViHSD (Vietnamese Hate Speech Detection Dataset)** for classifying Vietnamese text into three categories: CLEAN, OFFENSIVE, and HATE.

## Model Details

* **Base Model**: bert-base-multilingual-cased
* **Description**: mBERT fine-tuned cho bài toán phân loại Hate Speech tiếng Việt
* **Architecture**: mBERT (Multilingual BERT)
* **Dataset**: ViHSD (Vietnamese Hate Speech Detection Dataset)
* **Fine-tuning Framework**: HuggingFace Transformers + PyTorch
* **Task**: Hate Speech Classification (3 classes)

### Hyperparameters

* **Batch size**: `32`
* **Learning rate**: `2e-5`
* **Epochs**: `100`
* **Max sequence length**: `256`
* **Weight decay**: `0.01`
* **Warmup steps**: `500`
* **Early stopping patience**: `5`
* **Optimizer**: AdamW
* **Learning rate scheduler**: Cosine with warmup

## Dataset

Model was trained on **ViHSD (Vietnamese Hate Speech Detection Dataset)** containing ~10,000 Vietnamese comments from social media.

### Label Distribution:

- **CLEAN (0)**: CLEAN
- **OFFENSIVE (1)**: OFFENSIVE
- **HATE (2)**: HATE

### Label Descriptions:

* **CLEAN (0)**: Normal content without offensive language
* **OFFENSIVE (1)**: Mildly offensive or inappropriate content  
* **HATE (2)**: Hate speech, extremist language, severe threats

## Evaluation Results

The model was evaluated on test set with the following metrics:

* **Accuracy**: `0.9360`
* **Macro-F1**: `0.8044`
* **Weighted-F1**: `0.9317`
* **Macro-Precision**: `0.8850`
* **Macro-Recall**: `0.7518`

### Basic Usage

```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

# Load model and tokenizer
model_name = "visolex/mbert-hsd"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# Classify text
text = "Văn bản tiếng Việt cần phân loại"
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)

with torch.no_grad():
    outputs = model(**inputs)
    predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
    predicted_label = torch.argmax(predictions, dim=-1).item()

# Label mapping
label_names = {
    0: "CLEAN",
    1: "OFFENSIVE",
    2: "HATE"
}

print(f"Predicted label: {label_names[predicted_label]}")
print(f"Confidence scores: {predictions[0].tolist()}")
```

## Training Details

### Training Data
- **Dataset**: ViHSD (Vietnamese Hate Speech Detection Dataset)
- **Total samples**: ~10,000 Vietnamese comments from social media
- **Training split**: ~70%
- **Validation split**: ~15%
- **Test split**: ~15%

### Training Configuration
- **Framework**: PyTorch + HuggingFace Transformers
- **Optimizer**: AdamW
- **Learning Rate**: 2e-5
- **Batch Size**: 32
- **Max Length**: 256 tokens
- **Epochs**: 100 (with early stopping patience: 5)
- **Weight Decay**: 0.01
- **Warmup Steps**: 500


## Contact & Support

- **GitHub**: [ViSoLex Hate Speech Detection](https://github.com/visolex/hate-speech-detection)
- **Issues**: [Report Issues](https://github.com/visolex/hate-speech-detection/issues)
- **Questions**: Open a discussion on the model's Hugging Face page

## License

This model is distributed under the MIT License.

## Acknowledgments

- Base model: [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased)
- Dataset: ViHSD (Vietnamese Hate Speech Detection Dataset)
- Framework: [Hugging Face Transformers](https://huggingface.co/transformers)
- ViSoLex Toolkit

---