The general factor of personality (GFP) in natural language A deep learning approach

Using Large Language Models (LLMs), we tested the presence of a general factor of personality (GFP) in trait words in natural language (e.g., thousands of books and posts on internet). We included three set of trait words, extracted from well-known classical lexical studies on personality. The general factor we found represented a continuum of social desirable traits, similar to a typical GFP. Moreover, this LLM-based general factor correlated r = 0.86 with the general factor in the original Saucier and Goldberg (1997) data. The findings were robust regarding type of machine learning prompts and statistical methods used. The findings indicate that in natural language, a GFP exists that is similar to previous lexical studies using human raters.