---
license: mit
language: en
datasets:
- amananandrai/clickbait-dataset
metrics:
- accuracy
tags:
- sklearn
- text-classification
- clickbait
widget:
- text: "You Won't Believe What Happens Next!"
  example_title: "Clickbait Example"
- text: "Scientists Discover New Planet in Solar System"
  example_title: "Non-Clickbait Example"
---

# Clickbait Detection Model (Logistic Regression)

هذا نموذج تعلم آلة (Scikit-learn Pipeline) تم تدريبه لتصنيف عناوين الأخبار (Headlines) إلى "Clickbait" (عنوان مثير) أو "Not Clickbait" (عنوان عادي).

## 🚀 كيف تستخدم النموذج

تم حفظ النموذج كـ `Pipeline` كامل من `sklearn`، وهو يتضمن `TfidfVectorizer` و `LogisticRegression`. هذا يعني أنه يتعامل مع النص مباشرة.

```python
import joblib

# قم بتحميل النموذج من Hugging Face Hub
# (تأكد من تثبيت huggingface_hub: pip install huggingface_hub)
from huggingface_hub import hf_hub_download

model_path = hf_hub_download(repo_id="[Ma120]/[clickbait-detector]", filename="clickbait_model.pkl")
model = joblib.load(model_path)

# اختبر النموذج
headlines = [
    "You Won't Believe What Happens Next!",
    "Local Library Announces Summer Reading Program",
    "10 Signs You're a Genius (Number 7 Will Shock You)",
    "Government Passes New Budget Bill"
]

predictions = model.predict(headlines)

# 1 = Clickbait, 0 = Not Clickbait
for headline, pred in zip(headlines, predictions):
    label = "Clickbait" if pred == 1 else "Not Clickbait"
    print(f"[{label}] {headline}")

# يمكنك أيضاً الحصول على الاحتمالات
# probabilities = model.predict_proba(headlines)
# print(probabilities)