README.md

metadata

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

🍽️ 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.

---

📥 Dataset & Preprocessing

• Dataset Source: 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
Train Loss	0.470
Eval Loss	0.373
Accuracy	86.41%
Precision	87.01%
Recall	86.49%
F1-score	86.75%

⚙️ Training Configuration

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()

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:

[{"label": "Positive", "score": 0.96}]

---

2️⃣ Use Model with AutoModelForSequenceClassification

For batch processing & lower latency, use the AutoModel API:

from transformers import AutoModelForSequenceClassification, AutoTokenizer
import torch

model_name = "Abduuu/ArabReview-Sentiment"

# Load Model & Tokenizer
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Example Review
review = "الخدمة كانت بطيئة والطعام غير جيد."
inputs = tokenizer(review, return_tensors="pt")

# Perform Inference
with torch.no_grad():
    logits = model(**inputs).logits
    prediction = torch.argmax(logits).item()

label_map = {0: "Negative", 1: "Positive"}
print(f"Predicted Sentiment: {label_map[prediction]}")

---

🔬 Model Performance (Real Examples)

Review	Prediction
"الطعام كان رائعًا والخدمة ممتازة!"	✅ Positive
"التجربة كانت سيئة والطعام كان باردًا"	❌ Negative

---