|
|
--- |
|
|
license: openrail |
|
|
language: |
|
|
- en |
|
|
datasets: |
|
|
- newsmediabias/news-bias-full-data |
|
|
--- |
|
|
|
|
|
## Bias Classification Using Bert |
|
|
|
|
|
# Overview: |
|
|
|
|
|
This is a BERT based model designed to detect bias in text data enabling users to identify whether a given text is biased or non-biased. |
|
|
|
|
|
|
|
|
|
|
|
## Performance: |
|
|
|
|
|
The model's performance on unseen data is: |
|
|
|
|
|
### Non-biased Precision: 0.93 Recall: 0.96 |
|
|
|
|
|
### Biased Precision: 0.91 Recall: 0.88 |
|
|
|
|
|
## Overall accuracy : 0.93 |
|
|
|
|
|
|
|
|
|
|
|
## Usage |
|
|
|
|
|
To use the model, you can utilize the transformers library from Hugging Face: |
|
|
|
|
|
``` |
|
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("newsmediabias/UnBIAS-classification-bert") |
|
|
model = AutoModelForSequenceClassification.from_pretrained("newsmediabias/UnBIAS-classification-bert") |
|
|
|
|
|
classifier = pipeline("text-classification", model=model, tokenizer=tokenizer , device=0 if device.type == "cuda" else -1) |
|
|
|
|
|
|
|
|
classifier("Anyone can excel at coding.") |
|
|
``` |
|
|
|
|
|
|
|
|
 |
