Inferring Personality From Social Media Activity Using Large Language Models: Cross‐Model Agreement, Temporal Stability, and Convergent Validity With Self‐Reports
Journal of Personality · 2026
DOI: 10.1111/jopy.70019 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Personality, 2026. Verfasst von Davide Marengo und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychology, University of Turin, Turin, Italy. Hauptthemen laut MEDLINE: Large Language Models, Personality, Social Media, Self Report. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Large language models (LLMs) offer a promising approach to infer personality traits unobtrusively from digital footprints. However, the reliability and validity of these inferences remain underexplored.
Method
Gemini 1.5 Pro and GPT‐4o were used to infer Big Five traits from 2 years of Facebook posts by 1214 Italian users. Predictions were compared to self‐reports on the Ten‐Item Personality Inventory.
Results
LLM predictions underestimated Agreeableness and Conscientiousness, overestimated Extraversion, while Neuroticism and Openness closely aligned with self‐report means. On repeated prompting, Gemini 1.5 Pro inferences showed less variability than GPT‐4o, with both models achieving excellent reliability when aggregating inferences. Temporal stability was highest when combining predictions across LLMs, with test–retest correlations over 2 years ranging from 0.44 for Conscientiousness to 0.60 for Openness. Cross‐LLM agreement was highest when combining inferences from multiple time points, with correlations ranging from 0.58 for Neuroticism to 0.83 for Extraversion. Correlations with self‐reports were modest, reaching 0.27 for Extraversion, 0.24 for Agreeableness, 0.23 for Conscientiousness, 0.18 for Neuroticism, and 0.31 for Openness when combining LLM inferences across LLMs and time points.
Conclusion
These findings advance understanding of LLMs' potential for personality inference, highlighting the importance of aggregating inferences to enhance the reliability and validity of such assessments.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Psychology, University of Turin, Turin, Italy.
- Centre for Cognitive and Brain Sciences, Institute of Collaborative Innovation, University of Macau, Macau SAR, China.
- Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macau SAR, China.
- Department of Psychology, Faculty of Social Sciences, University of Macau, Macau SAR, China.
ORCID-Profile: Davide Marengo
Zitieren
APA
Marengo, D., Montag, C., & Settanni, M. (2026). Inferring Personality From Social Media Activity Using Large Language Models: Cross‐Model Agreement, Temporal Stability, and Convergent Validity With Self‐Reports. Journal of Personality. https://doi.org/10.1111/jopy.70019
Vancouver
Marengo D, Montag C, Settanni M. Inferring Personality From Social Media Activity Using Large Language Models: Cross‐Model Agreement, Temporal Stability, and Convergent Validity With Self‐Reports. Journal of Personality. 2026. doi:10.1111/jopy.70019
BibTeX
@article{Marengo2026,
author = {Marengo, Davide and Montag, Christian and Settanni, Michele},
title = {Inferring Personality From Social Media Activity Using Large Language Models: Cross‐Model Agreement, Temporal Stability, and Convergent Validity With Self‐Reports},
journal = {Journal of Personality},
year = {2026},
doi = {10.1111/jopy.70019}
}
EUVIMED