NBIAS: A Natural Language Processing Framework for Bias Identification in Text

TL;DR

This paper introduces NBIAS, a comprehensive NLP framework designed to detect biases in text across various domains, aiming to promote fair and ethical data usage through a transformer-based bias identification model.

Contribution

The paper presents a novel multi-layer framework with a transformer-based model for bias detection, including diverse datasets and a combined evaluation approach.

Findings

Accuracy improvements of 1% to 8% over baselines

Effective identification of bias words and phrases

Robust understanding of model functioning

Abstract

Bias in textual data can lead to skewed interpretations and outcomes when the data is used. These biases could perpetuate stereotypes, discrimination, or other forms of unfair treatment. An algorithm trained on biased data may end up making decisions that disproportionately impact a certain group of people. Therefore, it is crucial to detect and remove these biases to ensure the fair and ethical use of data. To this end, we develop a comprehensive and robust framework NBIAS that consists of four main layers: data, corpus construction, model development and an evaluation layer. The dataset is constructed by collecting diverse data from various domains, including social media, healthcare, and job hiring portals. As such, we applied a transformer-based token classification model that is able to identify bias words/ phrases through a unique named entity BIAS. In the evaluation procedure, we incorporate a blend of quantitative and qualitative measures to gauge the effectiveness of our models. We achieve accuracy improvements ranging from 1% to 8% compared to baselines. We are also able to generate a robust understanding of the model functioning. The proposed approach is applicable to a variety of biases and contributes to the fair and ethical use of textual data.