Conference Paper2026

AI-Driven Persona Generation for User-Centered Design Research: Evaluating Quality and Consistency Across Large Language Models

Md Jahidul Hossain Mekat, Kazi Samin Nawal, Anika Tabasum, Mohammed Tasdir Ahmmed, Ashraful Islam, M Ashraful Amin

2026 7th International Conference on Mobile Computing and Sustainable Informatics (ICMCSI)

IEEE, pp. 1918-1925

DOI: 10.1109/icmcsi67283.2026.11412817URL

Abstract

User personas are fictional characters that depict target users and are a key component in user-centered design processes. While personas offer useful design direction, their development historically is a time-consuming and resourceintensive task. This study explores the possibility of automated persona generation with large language models. AI-based persona generation presents a promising solution by simplifying and assisting with the crucial process. Structured prompt methods are employed in the research for generating personas. To compare these personas, the study utilized a mixed-method approach, utilizing qualitative measures like designer feedback alongside quantitative metrics for accuracy and diversity. Results show that AI-based personas are generally consistent, though they exhibit limitations such as bias and insensitivity to context. The findings suggest an approximate 96% reduction in time for persona creation, and give recommendations for integrating LLMs with persona development.

Keywords

  • large language models
  • prompt engineering
  • User-centered design
  • personas
  • persona consistency
  • algorithmic bias

CCDS Authors

Ashraful Islam, PhD
Ashraful Islam

Ashraful Islam, PhD

  • Center Director, CCDS
  • Director, HCI Wing

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh (IUB)

Published at

CHI, UIST, UbiComp, IJCNN, ICIP, HCII, ICDMW, BLP, IEEE Internet of Things Journal, JMIR, JMIR Human Factors, JMIR Formative Research, IEEE Access, Smart Agricultural Technology, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Human-Computer Interaction, AI for Social Good, AI for Public Health, AI for Impact

Prof. M Ashraful Amin, PhD
M Ashraful Amin, PhD

Prof. M Ashraful Amin, PhD

  • Founder Director, CCDS
  • Director, AI/ML, HCI & DS Wings

Professor

+1 more affiliation

Department of Information Sciences and Technology

George Mason University, USA

Published at

ACL, CHI, UbiComp, ECAI, WACV, PAKDD, IJCNN, ICPR, ICIP, HCII, CLEF, BLP, Scientific Reports, JMIR, IEEE Access, Smart Agricultural Technology, Frontiers in Computational Neuroscience, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Machine Learning, Cognitive & Vision Science, Cybernetics, Surveillance & Security, ICT in Education, Health, & Agriculture, Human-Computer Interaction, Internet of Things, Robotics

References

  1. 1.Ameet Deshpande, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan. (2023). Toxicity in chatgpt: Analyzing persona-assigned language models. , 1236–1270[10.18653/v1/2023.findings-emnlp.88]
  2. 2.Andreas Holzinger, Michaela Kargl, Bettina Kipperer, Peter Regitnig, Markus Plass, Heimo Muller. (2022). Personas for Artificial Intelligence (AI) an Open Source Toolbox. IEEE Access, 10, 23732–23747[10.1109/access.2022.3154776]
  3. 3.Joni Salminen, Kathleen Wenyun Guan, Soon-Gyo Jung, Bernard Jansen. (2022). Use Cases for Design Personas: A Systematic Review and New Frontiers. CHI Conference on Human Factors in Computing Systems, 1–21[10.1145/3491102.3517589]
  4. 4.Joni Salminen, Chang Liu, Wenjing Pian, Jianxing Chi, Essi Häyhänen, Bernard J Jansen. (2024). Deus Ex Machina and Personas from Large Language Models: Investigating the Composition of AI-Generated Persona Descriptions. , 1–20[10.1145/3613904.3642036]
  5. 5.Andreas Schuller, Doris Janssen, Julian Blumenröther, Theresa Maria Probst, Michael Schmidt, Chandan Kumar. (2024). Generating personas using LLMs and assessing their viability. , 1–7[10.1145/3613905.3650860]
  6. 6.Joongi Shin, Michael A. Hedderich, Bartłomiej Jakub Rey, Andrés Lucero, Antti Oulasvirta. (2024). Understanding Human-AI Workflows for Generating Personas. Designing Interactive Systems Conference, 757–781[10.1145/3643834.3660729]
  7. 7.Xishuo Zhang, Lin Liu, Yi Wang, Xiao Liu, Hailong Wang, Anqi Ren, Chetan Arora. (2023). PersonaGen: A Tool for Generating Personas from User Feedback. , 353–354[10.1109/re57278.2023.00048]
  8. 8.Ilkka Kaate, Joni Salminen, Soon-Gyo Jung, Trang Thi Thu Xuan, Essi Häyhänen, Jinan Y. Azem, Bernard J. Jansen. (2025). “You Always Get an Answer”: Analyzing Users’ Interaction with AI-Generated Personas Given Unanswerable Questions and Risk of Hallucination. , 1624–1638[10.1145/3708359.3712160]
  9. 9.Hao Li, Chenghao Yang, An Zhang, Yang Deng, Xiang Wang, Tat-Seng Chua. (2025). Hello Again! LLM-powered Personalized Agent for Long-term Dialogue. , 5259–5276[10.18653/v1/2025.naacl-long.272]
  10. 10.Nima Zargham, Mateusz Dubiel, Smit Desai, Thomas Mildner, Hanz-Joachim Belz. (2024). Designing AI Personalities: Enhancing Human-Agent Interaction Through Thoughtful Persona Design. , 490–494[10.1145/3701571.3701608]
  11. 11.Yutan Huang. (2024). Generating User Experience Based on Personas with AI Assistants. , 181–183[10.1145/3639478.3639810]
  12. 12.Aleksandr Farseev, Qi Yang, Andrey Filchenkov, Kirill Lepikhin, Yu-Yi Chu-Farseeva, Daron-Benjamin Loo. (2021). SoMin.ai. , 890–893[10.1145/3437963.3441714]
  13. 13.Ashraful Islam, Beenish Moalla Chaudhry. (2021). Identifying User Personas for Engagement with a COVID-19 Health Service Delivery Relational Agent. , 364–366[10.1145/3472307.3484658]
← All publications