Mustafa Akben, a faculty member at the Martha and Spencer Love School of Business, has created a machine learning model that is effective at assessing job performance and leadership potential simply by analyzing emails.
Share:
Can AI be used to identify candidates with leadership skills simply by reading their email responses to fictitious workplace situations?
Such was the challenge for assistant professor Mustafa Akben, who over the winter months developed a more accurate AI model than two dozen other entrants to an international competition hosted by the Society for Industrial and Organizational Psychology.
The SIOP 2023 Machine Learning competition focused on Natural Language Processing, a subfield of Artificial Intelligence focused on enabling computers to understand, interpret, and generate human language most recently in headlines due to its use in ChatGPT.
Here’s how the contest worked:
At a job assessment centre, candidates were asked to respond via email to fictitious scenarios they received during a one-day simulation. The way they analyzed the scenarios and the tone and content of their responses were evaluated by a panel of human judges.
The machine learning competition teams were provided with a spreadsheet of suggestions and responses from job applicants. However, they only received a limited number of scores. The task: Determine how human judges rated the second set of responses by building a model that looked at the scores for the first set.
Akben studies how artificial intelligence impacts human productivity and creativity. The AI model he developed had the best overall performance at predicting how judges had rated the second-largest group of candidates on the public council, leading to a virtual presentation he gave in April to in-person and online attendees at the SIOP annual conference. of 2023 in Boston.
I am absolutely thrilled with this win, both personally and professionally, said Akben. It’s amazing to see that all the hard work, dedication, and persistence I’ve poured into my research into AI, machine learning, and organizational behavior is paying off. This accomplishment reinforces my dedication to excellence within the Elon academic community. He is a great example to our students, illustrating the value of lifelong learning and striving for success in their areas of interest.
Plus, it really shows how interdisciplinary research can drive innovation and address some of the most complex challenges we face in the modern workplace today.
That doesn’t mean AI is on the verge of overtaking human evaluations for job performance and leadership traits, Akben said. Although her model was the best at predicting, on average, how candidates would be evaluated in the simulation, the resulting effect size was only moderate.
Akben said he would like to see effect sizes increase, and that part of the continued improvement of AI will also be in eliminating bias. Citing the parameters of competition, you noted that machines may not take into account that English is someone’s second language. Machines can count syntax or grammatical errors against those whose other talents are minimized by a focus on communication.
Akben joined Elon University’s Department of Management and Entrepreneurship in 2022 after receiving a bachelor’s degree from Marmara University, a master of science from the University of Pennsylvania, and a doctorate from Temple University.
His academic interests in proactivity, creativity, social network analysis, biohacking, and machine learning are reflected in many of the experiential learning assignments he has already created for his undergraduate management coursework principles.
As an educator, Akben said, I integrate emerging AI into my classroom, such as ChatGPT and other large language models, and my students often express their enthusiasm and fascination when exposed to these technologies. I look forward to collaborating on AI-related projects involving workplace or educational applications, creativity, and proactivity with Elon University students or faculty.
#Professor #Elon #wins #international #artificial #intelligence #competition