Personality Emulation Utilizing Large Language Models
Source abstract
Abstract
Fake identities have proven to be an effective methodology for conducting privacy and cybersecurity research; however, existing models are limited in their ability to interact with and respond to received communications. To perform privacy research in more complex Internet domains, withstand enhanced scrutiny, and persist long-term, fake identities must be capable of automatically generating responses while maintaining consistent behavior and personality. This work proposes a method for assigning personality to fake identities using the widely accepted psychometric Big Five model. Leveraging this model, the potential application of large language models (LLMs) to generate email responses that emulate human personality traits is investigated to enhance fake identity capabilities for privacy research at scale.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Personality Traits and Psychology · Mental Health via Writing · Topic Modeling
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA 24061, USA
National Security Institute, Virginia Tech, Blacksburg, VA 24061, USA
Funding
Commonwealth Cyber Initiative · VT National Security Institute’s Spectrum Dominance Division · National Science Foundation
References (58)
Show source-provided references
1. Ethical Considerations when Employing Fake Identities in Online Social Networks for Research10.1007/s11948-013-9473-0 ↗
2. Use & Abuse of Personal Information, Part II: Robust Generation of Fake IDs for Privacy Experimentation10.3390/jcp4030026 ↗
3. Use and Abuse of Personal Information, Part I: Design of a Scalable OSINT Collection Engine10.3390/jcp4030027 ↗
4. Gurajala, S., White, J.S., Hudson, B., and Matthews, J.N. (2015, January 27–29). Fake Twitter Accounts: Profile Characteristics Obtained Using an Activity-Based Pattern Detection Approach. Proceedings of the 2015 International Conference on Social Media & Society, Toronto, ON, Canada.10.1145/2789187.2789206 ↗
5. Khaled, S., El-Tazi, N., and Mokhtar, H.M.O. (2018, January 10–13). Detecting Fake Accounts on Social Media. Proceedings of the 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA.10.1109/BigData.2018.8621913 ↗
6. Elyusufi, Y., Elyusufi, Z., and Kbir, M.A. (2019, January 2–4). Social Networks Fake Profiles Detection Based on Account Setting and Activity. Proceedings of the 4th International Conference on Smart City Applications, Casablanca, Morocco.10.1145/3368756.3369015 ↗
7. Xu, H., and Demner Fushman, D. (2024). Large Language Model and Text Generation. Natural Language Processing in Biomedicine: A Practical Guide, Springer International Publishing.10.1007/978-3-031-55865-8 ↗
8. Mo, Y., Qin, H., Dong, Y., Zhu, Z., and Li, Z. (2024). Large Language Model (LLM) AI text generation detection based on transformer deep learning algorithm. arxiv.
9. Yuan, A., Coenen, A., Reif, E., and Ippolito, D. (2022, January 22–25). Wordcraft: Story Writing With Large Language Models. Proceedings of the 27th International Conference on Intelligent User Interfaces, Helsinki, Finland.10.1145/3490099.3511105 ↗
10. Wallwork, A. (2024). Using Large Language Models to Improve, Correct and Generate Your Emails. English for Academic Research: Grammar Exercises, Springer.10.1007/978-3-031-53168-2_29 ↗
11. Thiergart, J., Huber, S., and Übellacker, T. (2021). Understanding Emails and Drafting Responses—An Approach Using GPT-3. arXiv.
12. The Power of Personalization: A Systematic Review of Personality-Adaptive Chatbots10.1007/s42979-023-02092-6 ↗
13. An Introduction to the Five-Factor Model and Its Applications10.1111/j.1467-6494.1992.tb00970.x ↗
14. Foundation, M.B. (2025, May 15). Myers-Briggs Overview. Available online: https://www.myersbriggs.org/my-mbti-personality-type/myers-briggs-overview/.
15. The VIA Institute (2025, May 15). VIA Character Strengths Survey & Character Reports: Via Institute. Available online: https://www.viacharacter.org/.
16. Sutcliffe, R. (2023). A Survey of Personality, Persona, and Profile in Conversational Agents and Chatbots. arxiv.
17. Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., and Zurada, J.M. (2025). Personality of AI. Artificial Intelligence and Soft Computing, Springer.10.1007/978-3-031-84356-3 ↗
18. Li, T., Yan, X., Li, Y., Wang, J., Li, Q., Li, H., and Li, J. (2017). Neuronal Correlates of Individual Differences in the Big Five Personality Traits: Evidences from Cortical Morphology and Functional Homogeneity. Front. Neurosci., 11.10.3389/fnins.2017.00414 ↗
19. van der Woude, M., Dodds, T., and Torres, G. (2024). The ethics of open source investigations: Navigating privacy challenges in a gray zone information landscape. Journalism, 1–19.10.1177/14648849241274104 ↗
20. OSINT: A “Grey Zone”?10.1080/08850607.2014.900295 ↗
21. Rahman, M.S. (2025, May 15). The Art of Open Source Intelligence (OSINT): Addressing Cybercrime, Opportunities, and Challenges. Available online: https://ssrn.com/abstract=5281845.10.2139/ssrn.5281845 ↗
22. Desai, S., Dubiel, M., Zargham, N., Mildner, T., and Spillner, L. (2025). Personas Evolved: Designing Ethical LLM-Based Conversational Agent Personalities. arXiv.
23. Sun, G., Zhan, X., and Such, J. (2024, January 8–10). Building Better AI Agents: A Provocation on the Utilisation of Persona in LLM-based Conversational Agents. Proceedings of the 6th ACM Conference on Conversational User Interfaces, Luxembourg.10.1145/3640794.3665887 ↗
24. ’I’m Categorizing LLM as a Productivity Tool’: Examining Ethics of LLM Use in HCI Research Practices10.1145/3711000 ↗
25. Wang, T., Tao, M., Fang, R., Wang, H., Wang, S., Jiang, Y.E., and Zhou, W. (2024). AI PERSONA: Towards Life-long Personalization of LLMs. arXiv.
26. The Enneagram Institute (2025, June 04). Available online: https://www.enneagraminstitute.com/.
27. Bai, S., Zhu, T., and Cheng, L. (2012). Big-Five Personality Prediction Based on User Behaviors at Social Network Sites. arXiv.
28. Sitaraman, G., and Cock, M.d. (2014). Inferring Big 5 Personality from Online Social Networks. [Master’s Thesis, University of Washington Libraries].
29. Analyzing Big-Five Personality Traits of Indian Celebrities Using Online Social Media10.1007/s12646-017-0408-8 ↗
30. Karanatsiou, D., Sermpezis, P., Gruda, D., Kafetsios, K., Dimitriadis, I., and Vakali, A. (2022). My Tweets Bring All the Traits to the Yard: Predicting Personality and Relational Traits in Online Social Networks. ACM Trans. Web, 16.10.1145/3523749 ↗
31. Ivanov, T., and Penchev, V. (2024). AI Benchmarks and Datasets for LLM Evaluation. arXiv.
32. Vardhan, H. (2025, May 15). Top 10 LLM Models. Available online: https://medium.com/@harsh.vardhan7695/top-10-llms-model-e4d8c2c440bd.
33. Hendrycks, D., Burns, C., Basart, S., Zou, A., Mazeika, M., Song, D., and Steinhardt, J. (2021). Measuring Massive Multitask Language Understanding. arXiv.
34. Liang, P., Mai, Y., Somerville, J., Kaiyom, F., Lee, T., and Bommasani, R. (2025, May 15). Helm Lite V1.0.0: Lightweight and Broad Capabilities Evaluation. Available online: https://crfm.stanford.edu/2023/12/19/helm-lite.html.
35. Wu, Y., Mei, J., Yan, M., Li, C., Lai, S., Ren, Y., Wang, Z., Zhang, J., Wu, M., and Jin, Q. (2025). WritingBench: A Comprehensive Benchmark for Generative Writing. arXiv.
36. Wang, Y., Ma, X., Zhang, G., Ni, Y., Chandra, A., Guo, S., Ren, W., Arulraj, A., He, X., and Jiang, Z. (2024). MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark. arXiv.
37. Stanford (2025, May 15). A Holistic Framework for Evaluating Foundation Models. Available online: https://crfm.stanford.edu/helm/lite/latest/.
38. Sorokovikova, A., Fedorova, N., Rezagholi, S., and Yamshchikov, I.P. (2024). LLMs Simulate Big Five Personality Traits: Further Evidence. arXiv.
39. Frisch, I., and Giulianelli, M. (2024). LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models. arXiv.
40. Bo, J.Y., Xu, T., Chatterjee, I., Passarella-Ward, K., Kulshrestha, A., and Shin, D. (2025). Steerable Chatbots: Personalizing LLMs with Preference-Based Activation Steering. arXiv.
41. Sun, R., Li, X., Akella, A., and Konstan, J.A. (May, January 26). Multi-Prompting Scenario-based Movie Recommendation with Large Language Models: Real User Case Study. Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, Yokohama, Japan.
42. He, J.Z.Y., Pandey, S., Schrum, M.L., and Dragan, A. (2025). Context Steering: Controllable Personalization at Inference Time. arXiv.
43. Pan, K., and Zeng, Y. (2023). Do LLMs Possess a Personality? Making the MBTI Test an Amazing Evaluation for Large Language Models. arXiv.
44. Jiang, H., Zhang, X., Cao, X., Breazeal, C., Roy, D., and Kabbara, J. (2024, January 16–21). PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits. Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2024, Mexico City, Mexico.10.18653/v1/2024.findings-naacl.229 ↗
45. Klinkert, L.J., Buongiorno, S., and Clark, C. (2024, January 18–22). Evaluating the Efficacy of LLMs to Emulate Realistic Human Personalities. Proceedings of the Twentieth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, Lexington, KY, USA.10.1609/aiide.v20i1.31867 ↗
46. La Cava, L., and Tagarelli, A. (March, January 25). Open Models, Closed Minds? On Agents Capabilities in Mimicking Human Personalities through Open Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, Pennsylvania.
47. OpenAI (2025, May 15). Hello gpt-4o. Available online: https://openai.com/index/hello-gpt-4o.
48. OpenAI (2025, May 15). API Platform. Available online: https://openai.com/api.
49. DeepSeek (2025, May 15). DeepSeek. Available online: https://www.deepseek.com/.
50. NOUS RESEARCH (2025, May 15). Hermes 3. Available online: https://nousresearch.com/hermes3/.
51. Farabet, C. (2025, May 15). Introducing Gemma 3: The Most Capable Model You Can Run on a Single GPU or TPU. Available online: https://blog.google/technology/developers/gemma-3/.
52. Ollama (2025, May 15). Llama 3.3. Available online: https://ollama.com/library/llama3.3.
53. Anthropic (2025, May 15). Meet Claude: Anthropic. Available online: https://www.anthropic.com/claude.
54. Lambda (2025, May 15). Lambda Cloud API Documentation. Available online: https://cloud.lambda.ai/api/v1/docs#overview–response-types-and-formats.
55. Ollama (2025, May 15). Python & JavaScript Libraries · Ollama Blog. Available online: https://ollama.com/blog/python-javascript-libraries.
56. Anthropic (2025, May 15). Getting Started. Available online: https://docs.anthropic.com/en/api/getting-started.
57. Cultural bias and cultural alignment of large language models10.1093/pnasnexus/pgae346 ↗
58. Helt, A. (2025, May 15). What’s Your Writing Personality Type?. Available online: https://rootedinwriting.com/writing-personality/.