Team uses AI to match job seekers to ideal occupations
Marie Donlon | December 18, 2019People belonging to different occupations generally have distinct personality traits. This figure indicates the digital fingerprints of 1,200 individuals across nine occupations. Each dot corresponds to a user. Source: Paul X. McCarthyResearchers from the University of Melbourne, the University of New South Wales and the University of Sydney are using artificial intelligence (AI) to match a person to a profession based on their social media posts.
Taking a data driven approach to matching prospective employees to professions based on what the job seekers reveal about themselves and how they comport themselves online, the team first examined similarities shared by those in similar occupations.
To do this, the team looked at the occupations of over 100,000 Twitter users as listed in their respective profiles. The team then applied IBM’s cloud-based AI Watson along with a personality insights service to devise scores across 10 different personality traits as determined from the language the Twitter users included in their respective social media posts as an expression of their personalities.
Using that data, the team then applied machine learning algorithms to group together occupational personality traits into different categories and used that information to match job seekers with complementary occupations with a rate of accuracy of around 70%.
The developers of the system hope to improve that percentage so that the system will one day be used to match job seekers with their dream careers.
This is not the first time AI has been applied to job search applications. Despite recent claims that job hiring algorithms are biased, many companies are beginning to employ AI to make hiring decisions. Tech firm HireVue is using AI-based algorithms to help giants in the hospitality industry to make hiring decisions based on applicants' facial features. Meanwhile, researchers from the University of Minnesota are turning to machine learning to make predictions about an applicant’s performance and longevity.
The article "Social media-predicted personality traits and values can help match people to their ideal jobs" appears in the journal Proceedings of the National Academy of Sciences.