Inferring Grandiose Narcissism From Text: LIWC Versus Machine Learning

Authors

Andrew D. Cutler, Boston UniversityFollow
Stephen W. Carden, Georgia Southern UniversityFollow
Hannah L. Dorough, Georgia Southern UniversityFollow
Nicholas S. Holtzman, Georgia Southern UniversityFollow

Document Type

Article

Publication Date

2020

Publication Title

Journal of Language and Social Psychology

DOI

10.1177/0261927X20936309

ISSN

1552-6526

Abstract

People have long used language to infer associates’ personality. In quantitative research, the relationship is often analyzed by looking at correlations between a psychological construct and the Linguistic Inquiry and Word Count (LIWC)—a program that tabulates word frequencies. We compare LIWC to a machine learning (ML) language model on the task of predicting grandiose narcissism (valid N = 471).We use the ML model discussed in Cutler and Kulis and formulate it as an extension of LIWC. With a strict validation scheme, the LIWC prediction was not more accurate than chance. The ML representation did moderately better (R² = .043). This indicates that the ML model was able to preserve personality information where LIWC failed to do so, suggesting that precautions are warranted for social-personality research that relies solely on LIWC.

Comments

Sage Publishing Rights and Permissions

Recommended Citation

Cutler, Andrew D., Stephen W. Carden, Hannah L. Dorough, Nicholas S. Holtzman. 2020. "Inferring Grandiose Narcissism From Text: LIWC Versus Machine Learning." Journal of Language and Social Psychology, 40 (2): 260-276: SAGE Journal. doi: 10.1177/0261927X20936309
https://digitalcommons.georgiasouthern.edu/math-sci-facpubs/765