En Pipeline

🚀 Bias Recognizer Model

This model is designed to recognize biased words or phrases in a sentence, trained on the MBAD Dataset and built upon roberta - base from Spacy transformers.

🚀 Quick Start

You can test the model using the following examples:

• Biased example 1: "Billie Eilish issues apology for mouthing an anti - Asian derogatory term in a resurfaced video."
• Biased example 2: "Christians should make clear that the perpetuation of objectionable vaccines and the lack of alternatives is a kind of coercion."
• Biased example 3: "But, whether this switch constitutes a true win for the racist right or not, it’s clear that MAGA conservatives are highly attuned to how decisions are made in the White House and which positions they want to control."
• Biased example 4: "The fact that the abortion rate among American blacks is far higher than the rate for whites is routinely chronicled and mourned."

✨ Features

• Trained on the MBAD Dataset to identify biased words or phrases in sentences.
• Built on top of the roberta - base model provided by Spacy transformers.
• Associated with the model at https://huggingface.co/d4data/bias - detection - model.

📚 Documentation

Model Information

Model Performance

📄 License

This model is part of the Research topic "Bias and Fairness in AI" conducted by Deepak John Reji, Shaina Raza. If you use this work (code, model or dataset), please star at:

Bias & Fairness in AI, (2022), GitHub repository, <https://github.com/dreji18/Fairness - in - AI>