Identifying Words in Job Advertisements Responsible for Gender Bias in Candidate Ranking Systems via Counterfactual Learning

Abstract

Candidate ranking systems (CRSs) for vacancies can pose a significant risk in terms of ethical considerations if they are prone to gender bias or even have legal implications if discriminatory behavior is found. In the case of content-based CRSs, which identify suited candidates for a given job opening based on their resumes and the job advert, gender bias in these texts can also lead to discriminatory behavior of the CRS algorithm. We propose an algorithm to automatically identify gendered words in the job advertisement responsible for gender bias in the rankings. The algorithm determines the words with gendered connotations in the rank distribution for a given job advertisement using content-based job-candidate matching based on the actual biography of a candidate and a counterfactual version in which explicit gender-mentioning terms are swapped between male and female. To this end, we employ the neural network explainability method of integrated gradients to compute CRS’s association of the job advertisement words with the gender of candidates, which we call the bias score of words. At the core of our CRS is a cross-encoder architecture. To showcase and validate our approach, we conduct a study investigating the gendered words identified by the proposed algorithm in job advertisements from a private dataset and biographies from the BIOS dataset. We analyze the gendered words along multiple job categories and different linguistic categories. Finally, we statistically and qualitatively compare them with standardized lists manually created by social psychologists to contrast the gender associations CRSs make with human associations.

Citation

Deepak Kumar, Tessa Grosz, Elisabeth Greif, Navid Rekab-saz, Markus Schedl
Identifying Words in Job Advertisements Responsible for Gender Bias in Candidate Ranking Systems via Counterfactual Learning
Proceedings of the 3rd Workshop on Recommender Systems for Human Resources (RecSys in HR 2023) co-located with the 17th ACM Conference on Recommender Systems (RecSys 2023), 3490: 2023.

BibTeX

@inproceedings{Kumar2023Red_Words_RecSysHR,
    title = {Identifying Words in Job Advertisements Responsible for Gender Bias in Candidate Ranking Systems via Counterfactual Learning},
    author = {Kumar, Deepak and Grosz, Tessa and Greif, Elisabeth and Rekab-saz, Navid and Schedl, Markus},
    booktitle = {Proceedings of the 3rd Workshop on Recommender Systems for Human Resources (RecSys in HR 2023) co-located with the 17th ACM Conference on Recommender Systems (RecSys 2023)},
    editor = {Kaya, Mesut and Bogers, Toine and Graus, David and Johnson, Chris and Decorte, Jens-Joris},
    publisher = {CEUR-WS.org},
    url = {https://ceur-ws.org/Vol-3490/RecSysHR2023-paper_7.pdf},
    volume = {3490},
    month = {September},
    year = {2023}
}