Gendered Language in Resumes and its Implications for Algorithmic Bias in Hiring
By Prasanna Parasurama, João Sedoc. 2022
12 citations recorded by the source corpus.
Despite growing concerns around gender bias in NLP models used in algorithmic hiring, there is little empirical work studying the extent and nature of gendered language in resumes.Using a corpus of 709k resumes from IT firms, we train a series of models to classify the gender of the applicant, thereby measuring the extent of gendered information encoded in resumes.We also investigate whether it is possible to obfuscate gender from resumes by removing gender identifiers, hobbies, gender sub-space in embedding models, etc.We find that there is a significant amount of gendered information in resumes even after obfuscation.A simple Tf-Idf model can learn to classify gender with AUROC=0.75, and more sophisticated transformer-based models achieve AUROC=0.8.We further find that gender predictive values have low correlation with gender direction of embeddings – meaning that, what is predictive of gender is much more than what is “gendered” in the masculine/feminine sense.We discuss the algorithmic bias and fairness implications of these findings in the hiring context.
Subfields: General Health Professions, Natural Language Processing, Safety, Robustness & Interpretability, Philosophy
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
- Patrick Hall
- Inbal Magar
- Yarden Tal
- Roy Schwartz
- Yejin Choi
- Ronan Le Bras
- Samuel R. Bowman
- Jonathan Berant
In Safety, Robustness & Interpretability
Citations in the corpus
- Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias (2022, background): “For example, machine translation models have been shown to generate outputs based on gender stereotypes regardless of the context of the sentence (Stanovsky et al., 2019), and models rated male resumes higher than female ones (Parasurama and Sedoc, 2021).”
- Towards a Standard for Identifying and Managing Bias in Artificial Intelligence (2022, background): “In other scenarios, even when attempts are made to explicitly remove bias from training data, biases may still exist because of deep, complex connections within the text data [81, 144].”