---
tags:
- text-classification
- distilbert
- political-bias
- safetensors
license: apache-2.0
---

# political-bias-classifier
[![Hugging Face Model](https://img.shields.io/badge/Model%20Type-DistilBERT-blue.svg)](https://huggingface.co/models?search=distilbert) 
[![License](https://img.shields.io/badge/License-Apache%202.0-green.svg)](https://www.apache.org/licenses/LICENSE-2.0)

***

## 📖 Model Description

The **political-bias-classifier** is a fine-tuned **DistilBERT** model designed for **text classification** to identify and categorize political bias within a given text.

This model is intended to analyze the political leaning expressed in textual content, such as news headlines, articles, or social media commentary.

| Detail | Value |
| :--- | :--- |
| **Base Model** | DistilBERT |
| **Model Type** | Text Classification (Sequence Classification) |
| **Weights Format**| Safetensors (`model.safetensors`) |
| **License** | Apache-2.0 |
| **File Size** | ~268 MB |

***

## 🚀 Usage

You can easily use this model for inference with the Hugging Face `transformers` library.

### Using the Pipeline

The simplest way to get a prediction is by using the `pipeline` abstraction:

```python
from transformers import pipeline

# Initialize the classifier pipeline
classifier = pipeline(
    "text-classification", 
    model="Arstacity/political-bias-classifier"
)

# Example text for analysis
text_to_analyze = "The new trade bill is a crucial step towards economic growth, despite the opposition's claims of cronyism."

# Get the prediction
result = classifier(text_to_analyze)

print(result)
# Example Output Format (Actual labels and scores will vary): 
# [{'label': 'RIGHT_LEANING', 'score': 0.9542}]
```

### Direct Model Loading

For more control, you can load the tokenizer and model directly:

```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer

model_name = "Arstacity/political-bias-classifier"

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Load the model
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# You are now ready to perform tokenization and inference.
```
***
## Files in Repository

This repository contains all the necessary files for the DistilBERT model and tokenizer:

| File Name | Description |
| :--- | :--- |
| **model.safetensors** | The main model weights file (268 MB). |
| **config.json** | Configuration file for the model architecture |
| **vocab.txt**| Vocabulary file for the tokenizer |
| **tokenizer.json** | The tokenizer configuration file |
| **tokenizer_config.json** | Tokenizer metadata |
| **special_tokens_map.json** | Mapping for special tokens. |
***

License: Apache 2.0
---