Logo image
Back
WordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word Embeddings
Conference proceeding

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

Bhavya Ghai, Md Naimul Hoque and Klaus Mueller
Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, pp.1-7
01/01/2021
DOI: 10.1145/3411763.3451587
url
https://arxiv.org/pdf/2103.03598View
Open Access

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 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 like 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.
 Computer Science Technology Computer Science, Cybernetics Computer Science, Interdisciplinary Applications Computer Science, Theory & Methods Science & Technology

Details

Metrics

5 Record Views
14 Times Cited - Web of Science
Logo image