Adapt’s Kolawole Adebayo will examine how AI can be leveraged for bias-free recruitment and to increase diversity.
An Irish research project will examine how to use data and artificial intelligence to remove bias from the recruiting process.
The project will be led over three years by Kolawole Adebayo, a researcher at Adapt, the Science Foundation Ireland’s research center for digital content.
It has received funding from Enterprise Ireland and the European Union’s Horizon 2020 program under a Marie Curie Career-Fit Plus scholarship with a budget of € 259,550.
The goal is to use AI to end hiring discrimination and attract more diverse talent.
“Hiring bias occurs when candidates feel excluded or are viewed positively or negatively due to certain characterizations that have nothing to do with their abilities,” Adebayo said.
“Bias in hiring can lead to undue discrimination of quality candidates from disadvantaged or minority groups such as women, people of color and those from the LGBTIQ community.”
Adebayo’s project, called Laibre, will use advanced natural language processing techniques to eliminate biases in different HR workflows.
It will implement artificial intelligence models capable of understanding the content of HR documents to extract and remove information that can lead to unconscious bias and discrimination in the hiring attraction and selection stages.
“For example, at the job posting stage, Laibre will develop a domain-adapted language model to help rewrite inclusive job postings; while in the candidate review phase, Laibre will implement a context-sensitive information extraction model to identify and remove protected attributes such as gender, ethnicity, etc. “explained Adebayo.
“The project will implement models that learn candidates’ inherent suitability patterns from anonymous data for automated candidate review and selection towards competency-based hiring.”
The research will be supervised by Prof Brian Davis of Dublin City University’s School of Computing and the Adapter Center.
Davis said that considering that recruiting is an “economic gateway” for people to access job opportunities and earn income to support themselves and their families, the process must be “fair and impartial.”
“Factors like gender, ethnicity or sexual orientation shouldn’t determine who is hired or not. Furthermore, the issue can be seen not only from a moral point of view, but also from an economic point of view, “said David.
“Addressing bias in hiring will potentially reduce ‘bad hires’ while promoting diversity in the workplace, which aside from [from] addressing an important issue of equality also translates into greater innovation, productivity and profitability for employers “.
Adebayo will also work with industry partner Datalive Analytics in Ireland and Trinity College Dublin’s Learnovate Center, which focuses on industry-driven edtech research.
A Datalive Analytics spokesperson said the company is “building new solutions for the future of hiring, including eliminating bias from hiring and identifying skill gaps to foster rapid learning and development of employees and people. looking for a job”.
“The Laibre project will help transform recruiting into an efficient, analytical-based, impartial and risk-free ecosystem and, for us as a company, it will not come at a better time than this post-pandemic period where fair hiring practices can help put the right candidates to work ”.
Don’t lose the knowledge you need to be successful. Subscribe to Daily briefthe summary of the science fiction news needed to know the Silicon Republic.