Vector Personas: How UX Researchers Can Use AI to Bring New Dimension to Traditional Persona Development
Year: 2024
Type: conference-paper
Abstract: Personas, representing user groups with specific needs and behaviors, are crucial in user experience (UX) design. High-quality personas are based on robust user data; otherwise, they may cause more problems than they solve. Generative AI like ChatGPT shows potential in enhancing persona development by integrating diverse user data sources. However, its reliability is questionable due to its lack of contextual understanding and real-world experience. This paper introduces the concept of "Vector Personas," a method combining AI and traditional qualitative techniques to develop personas. Our UX team tested this approach by comparing personas created through traditional methods with those generated with AI assistance, using a structured comparison and triangulation of data from user feedback. Our study highlights the benefits and limitations of using AI in persona development. While AI can enhance efficiency and offer new insights, it cannot replace the depth of understanding provided by human research. The Vector Persona process optimizes persona development by balancing time investment and information quality, integrating AI outputs with human insights to create comprehensive and accurate user representations.
Authors: Claire Lauer, Danielle Storey, Romit Soley
Institution: Arizona State University
Language: English
Subfield: Human-Computer Interaction
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4403822419