Abdulrahman Al-Ghamdi
Update README.md
e06c224 verified
|
raw
history blame
1.99 kB
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

🍽️ Arabic Restaurant Review Sentiment Analysis πŸš€

πŸ“Œ Overview

This project fine-tunes a transformer-based model to analyze sentiment in Arabic restaurant reviews.
We utilized Hugging Face’s model training pipeline and deployed the final model as an interactive Gradio web app.

πŸ“₯ Data Collection

The dataset used for fine-tuning was sourced from Hugging Face Datasets, specifically:
πŸ“‚ Arabic Restaurant Reviews Dataset
It contains restaurant reviews in Arabic labeled with sentiment polarity.

πŸ”„ Data Preparation

  • Cleaning & Normalization:
    • Removed non-Arabic text, special characters, and extra spaces.
    • Normalized Arabic characters (e.g., Ψ₯, Ψ£, Ψ’ β†’ Ψ§, Ψ© β†’ Ω‡).
    • Downsampled positive reviews to balance the dataset.
  • Tokenization:
    • Used AraBERT tokenizer for efficient text processing.
  • Train-Test Split:
    • 80% Training | 20% Testing.

πŸ‹οΈ Fine-Tuning & Results

The model was fine-tuned using Hugging Face Transformers on a dataset of restaurant reviews.

πŸ“Š Evaluation Metrics

Metric Score
Eval Loss 0.5665
Accuracy 70.37%
Precision 70.36%
Recall 70.37%
F1-score 69.75%
Eval Runtime 11.5 sec

βš™οΈ Training Parameters

training_args = TrainingArguments(
    output_dir="./results",
    evaluation_strategy="steps",
    eval_steps=200,
    per_device_train_batch_size=2,
    per_device_eval_batch_size=2,
    num_train_epochs=5,
    weight_decay=0.01,
    learning_rate=3e-5,
    logging_steps=100,
    fp16=True,
    report_to="none"
)