Gender Bias Detection in Educational Materials
An NLP pipeline for detecting gender bias in text.
TL;DR: The work aims to use NLP for automatic, quantitative analysis of educational text regarding gender bias within a taxonomy framework, which informs educators about bias patterns in textbooks, lexical resources (WordNet), and assessment item design.
About
The work is with Haotian Zhu, Prof. Mari Ostendorf and Prof. Fei Xia.
I designed the pipeline and conducted the experiments and statistical analysis for the lexical resource dataset.
Abstract
Gender bias has been extensively studied in both the educational field and the Natural Language Processing (NLP) field, the former using human coding to identify patterns associated with and causes of gender bias in text and the latter to detect, measure and mitigate gender bias in NLP output and models. This work aims to use NLP to facilitate automatic, quantitative analysis of educational text within the framework of a gender bias taxonomy. Analyses of both educational texts and a lexical resource (WordNet) reveal patterns of bias that can inform and aid educators in updating textbooks and lexical resources and in designing assessment items.
Paper
We have submitted the paper to ACL 2024. (preview)
News
Our paper is admitted by the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP) of ACL Anthology!
Code
The code will be released soon!