If you say a few words, generative AI can understand who you are—perhaps even better than your closest family and friends. A groundbreaking study from the University of Michigan has found that widely available generative AI models, such as ChatGPT, Claude, and LLaMa, can predict personality, key behaviors, and daily emotions with remarkable accuracy.
“What this study shows is AI can also help us understand ourselves better, providing insights into what makes us most human, our personalities,” said Aidan Wright, the study’s first author and a University of Michigan professor of psychology and psychiatry. “Lots of people may find this of interest and useful. People have long been interested in understanding themselves better. Online personality questionnaires, some valid and many of dubious quality, are enormously popular.”
AI as a Judge of Personality
The researchers explored whether AI programs like ChatGPT and Claude could function as general “judges” of personality. To test this, they had the AI analyze people’s own words—either through short daily video diaries or longer recordings of spontaneous thoughts—and then answer personality questions as each person would. The study incorporated stories and reflections from over 160 individuals, collected in both real-life and laboratory settings.
The results were striking: the AI’s personality scores closely matched how individuals rated themselves, often surpassing the accuracy of assessments made by friends or family. Older text-analysis methods paled in comparison to these advanced AI systems.
“We were taken aback by just how strong these associations were, given how different these two data sources are,” Wright remarked, highlighting the unexpected precision of AI in this context.
Implications for Understanding Human Psychology
The study’s findings suggest that personality traits naturally manifest in our everyday thoughts, words, and stories—even when we are not consciously describing ourselves. AI’s personality ratings were also able to predict real-life aspects such as emotions, stress levels, social behavior, and even mental health conditions or treatment.
Chandra Sripada, a University of Michigan professor of philosophy and psychiatry, noted that the findings bolster the long-held belief that language provides profound insights into psychological traits like personality and mood. He emphasized that open-ended writing and speech can serve as powerful tools for understanding personality, with generative AI enabling researchers to analyze such data swiftly and accurately.
Unanswered Questions and Future Directions
Despite these promising results, significant questions remain. The study relied on individuals rating their own personalities, without comparing AI assessments to those made by friends or family. Additionally, it did not explore how results might vary across different demographics such as age, gender, or race.
Researchers are also uncertain whether AI and humans rely on the same cues—or if AI might eventually surpass self-reports in predicting major life outcomes like relationships, education, health, or career success.
“The study shows that AI can reliably uncover personality traits from everyday language, pointing to a new frontier in understanding human psychology,” said Colin Vize, assistant professor of psychology at the University of Pittsburgh.
Whitney Ringwald, assistant professor of psychology at the University of Minnesota, added that the results “really highlight how our personality is infused in everything we do, even down to our mundane, everyday experiences and passing thoughts.”
The study’s authors include Johannes Eichstaedt of Stanford University and Mike Angstadt and Aman Taxali, both from the University of Michigan. The findings have been published in the journal Nature Human Behavior.
Contact: Jared Wadley.
Study: Generative AI predicts personality traits based on open-ended narratives (DOI: 10.1038/s41562-025-02389-x)
