Dimitri van der Linden , Andrew Cutler , Putri A. van der Linden , Curtis S. Dunkel
{"title":"The general factor of personality (GFP) in natural language: A deep learning approach","authors":"Dimitri van der Linden , Andrew Cutler , Putri A. van der Linden , Curtis S. Dunkel","doi":"10.1016/j.jrp.2025.104635","DOIUrl":null,"url":null,"abstract":"<div><div>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 <em>r</em> = 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.</div></div>","PeriodicalId":48406,"journal":{"name":"Journal of Research in Personality","volume":"117 ","pages":"Article 104635"},"PeriodicalIF":3.1000,"publicationDate":"2025-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Research in Personality","FirstCategoryId":"102","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0092656625000674","RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PSYCHOLOGY, SOCIAL","Score":null,"Total":0}
引用次数: 0
Abstract
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.
使用大型语言模型(llm),我们测试了自然语言(例如,成千上万的书籍和互联网上的帖子)特征性词汇中人格的一般因素(GFP)的存在。我们收录了三组特征词,摘自著名的经典人格词汇研究。我们发现的一般因素代表了社会理想特征的连续体,类似于典型的GFP。此外,基于llm的一般因子与Saucier and Goldberg(1997)原始数据中的一般因子相关r = 0.86。关于机器学习提示类型和使用的统计方法,研究结果是稳健的。研究结果表明,在自然语言中,存在一种与先前使用人类评分器进行的词汇研究相似的GFP。
期刊介绍:
Emphasizing experimental and descriptive research, the Journal of Research in Personality presents articles that examine important issues in the field of personality and in related fields basic to the understanding of personality. The subject matter includes treatments of genetic, physiological, motivational, learning, perceptual, cognitive, and social processes of both normal and abnormal kinds in human and animal subjects. Features: • Papers that present integrated sets of studies that address significant theoretical issues relating to personality. • Theoretical papers and critical reviews of current experimental and methodological interest. • Single, well-designed studies of an innovative nature. • Brief reports, including replication or null result studies of previously reported findings, or a well-designed studies addressing questions of limited scope.