ChatGPT can generate personality tests and predict people's responses before they take them
In iScience, scientists outline how they developed a method for generating personality assessment questionnaires with ChatGPT from any source text. To test the method, they applied it to both the DSM-5 and, as a deliberately unconventional example, an astrology textbook. Not only could ChatGPT be used to create and validate these questionnaires, but it could also accurately predict…
Researchers from the Hebrew University of Jerusalem have developed a method for generating personality assessment questionnaires using AI language model ChatGPT. They applied this method to both the Diagnostic and Statistical Manual of Mental Disorders (DSM-5) and an astrology textbook. ChatGPT not only created these questionnaires but also accurately predicted population-level responses before the surveys were administered.
The study suggests that LLMs like ChatGPT have an embedded understanding of human personality within their algorithms, as personality traits are reflected in language. The researchers found that the DSM-5-derived questionnaire showed high internal consistency and could predict life outcomes like depression, anxiety, and well-being at levels comparable to the Big Five personality questionnaire.
However, the astrology-based questionnaire showed weak internal consistency, indicating that the personality traits assigned to zodiac signs lack scientific grounding. Despite this limitation, both questionnaires could predict responses before being taken, revealing that LLMs have an inherent understanding of population-level personality dynamics.
The study highlights the potential of AI tools in creating and validating clinical personality assessments rapidly and efficiently.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
