Using AI for User Representation: An Analysis of 83 Persona Prompts

TL;DR

This paper analyzes 83 prompts used with large language models to generate user personas, revealing trends, common formats, and methodological practices in computational user representation.

Contribution

It provides a comprehensive analysis of persona prompts, highlighting prevalent formats, attributes, and research practices, and discusses implications for user modeling.

Findings

Most prompts generate single, concise personas.

Text and numbers are the main formats for persona attributes.

Structured formats like JSON are frequently required.

Abstract

We analyzed 83 persona prompts from 27 research articles that used large language models (LLMs) to generate user personas. Findings show that the prompts predominantly generate single personas. Several prompts express a desire for short or concise persona descriptions, which deviates from the tradition of creating rich, informative, and rounded persona profiles. Text is the most common format for generated persona attributes, followed by numbers. Text and numbers are often generated together, and demographic attributes are included in nearly all generated personas. Researchers use up to 12 prompts in a single study, though most research uses a small number of prompts. Comparison and testing multiple LLMs is rare. More than half of the prompts require the persona output in a structured format, such as JSON, and 74% of the prompts insert data or dynamic variables. We discuss the implications of increased use of computational personas for user representation.