WordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word Embeddings

TL;DR

WordBias is an interactive visual tool that helps researchers discover and explore intersectional biases in static word embeddings by visualizing associations with social groups.

Contribution

This work introduces WordBias, a novel interactive visualization tool for identifying intersectional biases in word embeddings, enhancing bias detection capabilities.

Findings

Uncovered biases against groups like Black Muslim Males and Poor Females.

Demonstrated effectiveness through a case study.

Received positive expert feedback on usability.

Abstract

Intersectional bias is a bias caused by an overlap of multiple social factors like gender, sexuality, race, disability, religion, etc. A recent study has shown that word embedding models can be laden with biases against intersectional groups like African American females, etc. The first step towards tackling such intersectional biases is to identify them. However, discovering biases against different intersectional groups remains a challenging task. In this work, we present WordBias, an interactive visual tool designed to explore biases against intersectional groups encoded in static word embeddings. Given a pretrained static word embedding, WordBias computes the association of each word along different groups based on race, age, etc. and then visualizes them using a novel interactive interface. Using a case study, we demonstrate how WordBias can help uncover biases against intersectional groups like Black Muslim Males, Poor Females, etc. encoded in word embedding. In addition, we also evaluate our tool using qualitative feedback from expert interviews. The source code for this tool can be publicly accessed for reproducibility at github.com/bhavyaghai/WordBias.