UnBIAS Classification Model Card

Model Description

UnBIAS is a state-of-the-art model designed to classify texts based on their bias levels. The model categorizes texts into three classes: "Highly Biased", "Slightly Biased", and "Neutral".

Model Architecture

The model is built upon the bert-base-uncased architecture and has been fine-tuned on a custom dataset for the specific task of bias detection.

Dataset

The model was trained on a dataset containing news articles from various sources, annotated with one of the three bias levels. The dataset contains:

• Highly Biased: 4000 articles
• Slightly Biased: 4000 articles
• Neutral: 4000 articles

Training Procedure

The model was trained using the Adam optimizer for 10 epochs.

Performance

On our validation set, the model achieved:

• Accuracy: 95%
• F1 Score (Highly Biased): 89%
• F1 Score (Slightly Biased): 85%
• F1 Score (Neutral): 82%

(Replace placeholders with actual performance metrics.)

How to Use

To use this model for text classification, use the following code:

from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
tokenizer = AutoTokenizer.from_pretrained("newsmediabias/UnBIAS-classifier")
model = AutoModelForSequenceClassification.from_pretrained("newsmediabias/UnBIAS-classifier")

classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)
result = classifier("Women are bad driver.")
print(result)

Developed by Shaina Raza