Successful teams are often described as being greater than the sum of their parts, as the saying goes. But how do you find the best interpersonal chemistry and team dynamics when people are working with AI agents?
In a first-of-its-kind study, Carey Assistant Professor Harang Ju and MIT Professor Sinan Aral conducted a controlled, randomized trial to determine the best personality pairings for people and AI agents.
“In the literature, we found several research studies that showed different types of people or personality types actually get different results using AI,” Ju explained. “The question that we asked was: can we vary the type of AI that people are using by changing and randomizing the personalities of the AI?”
For their study, Ju and Aral randomly paired 1,258 participants with AI agents programmed to exhibit varying levels of the Big Five personality traits, a widely accepted psychology framework for categorizing human personalities. The human participants were categorized using the same framework, which includes the traits of openness, conscientiousness, extraversion, agreeableness, and neuroticism. The human-AI teams were then asked to produce more than 7,000 display ads, which we evaluated for quality and performance using 1,995 independent human raters and a field experiment on X that generated nearly five million impressions.
The results showed that ad quality significantly influenced ad performance, measured by click-through rates and cost-per-click. Human and AI personalities individually shaped ad quality and teamwork, and when examined together, human-AI personality pairings directly affected ad quality outcomes. The experiment demonstrated that personality pairing affected ad quality, teamwork, and real-world ad performance. For example, extraverted humans paired with conscientious AI produced the lowest-quality ads.
The researchers were most surprised by the combinations of personality pairings between humans and AI, and they believe their large-scale experimental evaluation of personality pairing in human-AI collaboration is an important first step toward robust AI personalization. The results could pave the way for better hiring and team-building strategies.
“Strategically pairing AI personalities with human traits has the potential to transform collaborative workflows and performance in human-AI teams,” said Ju. “You can't manipulate the personalities of humans, but we know we can change the personalities of AI agents and get results. This means that you can actually hire for skills and traits that actually matter for the role and less on whether you can use an AI better or not.”
Ju and Aral’s study “Personality Pairing Improves Human-AI Collaboration” appears in the August edition of the journal Proceedings of the National Academy of Sciences.
