---
license: mit
base_model: alger-ia/dziribert
tags:
- generated_from_trainer
- text-classification
- arabic
- algerian
- darija
- french
datasets:
- algerian-telecom-comments
language:
- ar
- fr
metrics:
- accuracy
- f1
model-index:
- name: dziribert-algerie-telecom-v1
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: Algerian Telecom Comments
      type: custom
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.87
    - name: F1 Score
      type: f1
      value: 0.85
---

# DziriBERT Algérie Télécom Classifier

This model is a fine-tuned version of [alger-ia/dziribert](https://huggingface.co/alger-ia/dziribert) for classifying Algerian telecom customer comments into urgency levels.

## Model Description

- **Base Model**: DziriBERT (BERT for Algerian Arabic)
- **Task**: Text Classification
- **Languages**: Arabic, French, Algerian Darija
- **Classes**: 5 urgency levels
  - `High_Urgency`: عاجل جداً
  - `Medium_Urgency`: متوسط الأهمية  
  - `Low_Medium_Urgency`: منخفض-متوسط
  - `Low_Urgency`: منخفض الأهمية
  - `No_Urgency`: لا توجد أهمية

## Usage

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

tokenizer = AutoTokenizer.from_pretrained("tarekAeb/dziribert-algerie-telecom-v1")
model = AutoModelForSequenceClassification.from_pretrained("tarekAeb/dziribert-algerie-telecom-v1")

classifier = pipeline("text-classification", 
                     model=model, 
                     tokenizer=tokenizer)

# Example
result = classifier("الانترنت ما يخدم من البارح")
print(result)
# [{'label': 'High_Urgency', 'score': 0.89}]
```

## Training Data

- **Dataset**: 9,771 customer comments from Algerian telecom social media
- **Sources**: Facebook, Instagram, Twitter posts
- **Preprocessing**: Text cleaning, normalization, augmentation

## Performance

- **Accuracy**: 87%
- **F1-Score**: 85%
- **Training Strategy**: Layer freezing, hyperparameter optimization

## Demo

Try the live demo: [Comment Genie](https://your-demo-url.com)