Abstract
This article reviews the linguistic behavior features of social media users that enable accurate psychological profiling by large language models. Drawing on recent research by Peters, Matz, and Gelfand (2024), the analysis examines how textual elements such as status updates encode personality traits including Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. The findings reveal significant demographic variations in linguistic expression and highlight implications for privacy, ethics, and AI governance in digital contexts.References
1. Back, M. D., Stopfer, J. M., Vazire, S., Gaddis, S., Schmukle, S. C., Egloff, B., & Gosling, S. D. (2010). Facebook profiles reflect actual personality, not self- idealization. Psychological Science, *21*(3), 372–374.
2. Bolukbasi, T., Chang, K.-W., Zou, J., Saligrama, V., & Kalai, A. (2016). Man is to computer programmer as woman is to homemaker? Debiasing word embeddings. Proceedings of the 30th International Conference on Neural Information Processing Systems, 4356–4364.
3. Hu, M. (2020). Cambridge Analytica’s black box. Big Data & Society, *7*(2), 1–6.
4. Kondakciu, K., Souto, M., & Zayer, L. T. (2021). Self-presentation and gender on social media: An exploration of the expression of “authentic selves”. Qualitative Market Research: An International Journal, *25*(1), 80–99.
5. Park, G., Schwartz, H. A., Eichstaedt, J. C., Kern, M. L., Kosinski, M., Stillwell, D. J., Ungar, L. H., & Seligman, M. E. P. (2015). Automatic personality assessment through social media language. Journal of Personality and Social Psychology, *108*(6), 934–952.
6. Peters, H., Matz, S. C., & Gelfand, M. (2024). Large language models can infer psychological dispositions of social media users. PNAS Nexus, *3*(6), pgae231.
7. Tifferet, S., & Vilnai-Yavetz, I. (2014). Gender differences in Facebook self- presentation: An international randomized study. Computers in Human Behavior, *35*, 388–
8. Vazire, S., & Gosling, S. D. (2004). e-Perceptions: Personality impressions based on personal websites. Journal of Personality and Social Psychology, *87*(1), 123–132.
9. Wan, Y., Pu, G., Sun, J., Garimella, A., Chang, K.-W., & Peng, N. (2023). BiasAsker: Measuring the bias in conversational AI systems. arXiv preprint arXiv:2305.12434. Youyou, W., Kosinski, M., & Stillwell, D. (2015). Computer-based personality judgments are more accurate than those made by humans. Proceedings of the National Academy of Sciences, *112*(4), 1036–1040.