Balancing Gender Bias in Job Advertisements With Text-Level Bias Mitigation

Abstract

Despite progress toward gender equality in the labor market over the past few decades, gender segregation in labor force composition and labor market outcomes persists. Evidence has shown that job advertisements may express gender preferences, which may selectively attract potential job candidates to apply for a given post and thus reinforce gendered labor force composition and outcomes. Removing gender-explicit words from job advertisements does not fully solve the problem as certain implicit traits are more closely associated with men, such as ambitiousness, while others are more closely associated with women, such as considerateness. However, it is not always possible to find neutral alternatives for these traits, making it hard to search for candidates with desired characteristics without entailing gender discrimination. Existing algorithms mainly focus on the detection of the presence of gender biases in job advertisements without providing a solution to how the text should be (re)worded. To address this problem, we propose an algorithm that evaluates gender bias in the input text and provides guidance on how the text should be debiased by offering alternative wording that is closely related to the original input. Our proposed method promises broad application in the human resources process, ranging from the development of job advertisements to algorithm-assisted screening of job applications.

Responsible AI for labour market equality (BIAS)

“…For example, the computational team found that, by collaborating closely with the sociology team, they were able to solidify concepts and methods, and make their analysis more meaningful. This process informed work on a paper where the sociology team took the lead in developing a list of gender-related words in job advertisements, which the computing team then used to refine their approach to gender bias mitigation (Hu et al, 2022). As explained by a computing team member: 'Although we could, probably, rely on common sense, we don't have to in this project.…”

Unveiling Gender Biases in Recruitment: A Natural Language Processing Approach

“…Research has provided clear evidence that job postings, explicitly and implicitly, signal employers' preferences for certain types of candidates, which may lead to potential gender biases. There is an indication that the language and wording used in UK STEM job advertisements are biased toward a masculine orientation [29]; and even that there is a positive association between male-biased job postings and a male-dominated STEM workforce [30].…”

Reifying discrimination on the path to school leadership: Black female principals’ experiences of district hiring/promotion practices

“…They may work to preemptively analyze existing materials for racialized or gendered language (Hu et al, 2022) as well as work to emphasize skills rather than "fit" (Palmer and Mullooly, 2015).…”