How Is Generative AI Used for Persona Development?: A Systematic Review of 52 Research Articles

2025-04-07

AI Summary

Generative AI (GenAI) faces critical challenges in user profiling, including “monolithic homogenization” driven by dominant closed-source models, insufficient human-AI collaboration mechanisms, and weak evaluation frameworks. This study conducts a systematic literature review (SLR) of 52 peer-reviewed papers published between 2022 and 2024 to analyze GenAI applications across four profiling stages: data acquisition, segmentation, enrichment, and evaluation. It is the first to empirically identify evaluation gaps and inadequate human oversight as primary bottlenecks. The work proposes a comprehensive research roadmap integrating large language model (LLM) deployment, human-in-the-loop collaboration, ethical assessment, and cross-disciplinary integration. Twelve prioritized research directions are explicitly delineated—spanning algorithmic fairness, explainability, domain adaptation, real-time profiling, and regulatory alignment—to advance both theoretical understanding and industrial implementation. The framework bridges academic rigor with practical applicability, offering actionable guidance for researchers and practitioners developing responsible, adaptive user profiling systems.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Natural Language Processing: Generation
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Although Generative AI (GenAI) has the potential for persona development, many challenges must be addressed. This research systematically reviews 52 articles from 2022-2024, with important findings. First, closed commercial models are frequently used in persona development, creating a monoculture Second, GenAI is used in various stages of persona development (data collection, segmentation, enrichment, and evaluation). Third, similar to other quantitative persona development techniques, there are major gaps in persona evaluation for AI generated personas. Fourth, human-AI collaboration models are underdeveloped, despite human oversight being crucial for maintaining ethical standards. These findings imply that realizing the full potential of AI-generated personas will require substantial efforts across academia and industry. To that end, we provide a list of research avenues to inspire future work.

Problem

• Evaluating gaps in AI-generated persona evaluation methods
• Exploring human-AI collaboration models for ethical standards
• Addressing monoculture risks from closed commercial GenAI models

Innovation

• Closed commercial models dominate persona development
• GenAI applied in multiple persona development stages
• Human-AI collaboration models need further development