README.md

---
license: apache-2.0
datasets:
- hadyelsahar/ar_res_reviews
language:
- ar
metrics:
- accuracy
- precision
- recall
- f1
base_model:
- aubmindlab/bert-base-arabertv02
pipeline_tag: text-classification
tags:
- arabic
- sentiment-analysis
- transformers
- huggingface
- bert
- restaurants
- fine-tuning
- nlp
inference: true
---

# 🍽️ Arabic Restaurant Review Sentiment Analysis 🚀  

## 📌 Overview  
This **fine-tuned AraBERT model** classifies **Arabic restaurant reviews** as **Positive** or **Negative**.  
It is based on **aubmindlab/bert-base-arabertv2** and fine-tuned using **Hugging Face Transformers**.

### **🔥 Why This Model?**  
✅ **Trained on Real Restaurant Reviews** from the **Hugging Face Dataset**.  
✅ **Fine-tuned with Full Training** (not LoRA or Adapters).  
✅ **Balanced Dataset** (2418 Positive vs. 2418 Negative Reviews).  
✅ **High Accuracy & Performance** for Sentiment Analysis in Arabic.  

---

## 🚀 **Try the Model Now!**  
**Run inference directly from the Hugging Face Space:**  

<p align="center">
  <a href="https://huggingface.co/spaces/Abduuu/Arabic-Reviews-Sentiment-Analysis">
    <img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-lg-dark.svg" alt="Open in HF Spaces" width="280px">
  </a>
</p>

---

## **📥 Dataset & Preprocessing**
- **Dataset Source**: [`hadyelsahar/ar_res_reviews`](https://huggingface.co/datasets/hadyelsahar/ar_res_reviews)
- **Text Cleaning**:
  - Removed **non-Arabic text**, special characters, and extra spaces.
  - Normalized Arabic characters (`إ, أ, آ → ا`, `ة → ه`).
  - Balanced **Positive & Negative** sentiment distribution.
- **Tokenization**:
  - Used **AraBERT tokenizer** (`aubmindlab/bert-base-arabertv2`).
- **Train-Test Split**:
  - **80% Training** | **20% Testing**.

---

## **🏋️ Training & Performance**
The model was fine-tuned using **Hugging Face Transformers** with the following hyperparameters:

### **📊 Final Model Results**
| Metric       | Score  |
|-------------|--------|
| **Eval Loss**  | `0.354245` |
| **Accuracy**   | `87.40%` |
| **Precision**  | `85.28%` |
| **Recall**     | `86.33%` |
| **F1-score**   | `85.81%` |

### **⚙️ Training Configuration**
```python
training_args = TrainingArguments(
    output_dir="./results",
    evaluation_strategy="epoch",
    save_strategy="epoch",
    per_device_train_batch_size=8,
    per_device_eval_batch_size=8,
    num_train_epochs=4,
    weight_decay=1,
    learning_rate=1e-5,
    lr_scheduler_type="cosine",
    warmup_ratio=0.1,
    fp16=True,
    save_total_limit=2,
    gradient_accumulation_steps=2,
    load_best_model_at_end=True,
    max_grad_norm=1.0,
    metric_for_best_model="eval_loss",
    greater_is_better=False,
)
```

---

## **💡 Usage**
### **1️⃣ Quick Inference using `pipeline()`**
```python
from transformers import pipeline

model_name = "Abduuu/ArabReview-Sentiment"
sentiment_pipeline = pipeline("text-classification", model=model_name)

review = "الطعام كان رائعًا والخدمة ممتازة!"
result = sentiment_pipeline(review)
print(result)
```
✅ **Example Output:**
```json
[{'label': 'Positive', 'score': 0.91551274061203}]
```

---

## 📉 Training & Validation Loss Curve

The model was trained for **4 epochs**, and the **best model** was selected at **Epoch 2** (lowest validation loss).

![Loss Curve](https://huggingface.co/Abduuu/ArabReview-Sentiment/resolve/main/Loss-Graph.png)

---

## 📊 Dataset Class Distribution
![Class Distribution](https://huggingface.co/Abduuu/ArabReview-Sentiment/resolve/main/Class_dist.png)

---

For questions or collaborations, feel free to reach out! 🚀

---