Improved prompting and process for writing user personas with LLMs, using qualitative interviews: Capturing behaviour and personality traits of users

TL;DR

This paper introduces an enhanced workflow for creating user personas using large language models and qualitative interview analysis, emphasizing improved prompting and larger thematic pools enabled by recent LLM capabilities.

Contribution

It presents a novel workflow leveraging advanced prompting and thematic analysis with GPT-3.5-Turbo-16k for more accurate user persona creation from qualitative data.

Findings

Enhanced persona creation process with larger thematic pools

Demonstrated capacity of LLMs to capture user traits

Reflections on the relationship between LLM-based and traditional personas

Abstract

This draft paper presents a workflow for creating User Personas with Large Language Models, using the results of a Thematic Analysis of qualitative interviews. The proposed workflow uses improved prompting and a larger pool of Themes, compared to previous work conducted by the author for the same task. This is possible due to the capabilities of a recently released LLM which allows the processing of 16 thousand tokens (GPT3.5-Turbo-16k) and also due to the possibility to offer a refined prompting for the creation of Personas. The paper offers details of performing Phase 2 and 3 of Thematic Analysis, and then discusses the improved workflow for creating Personas. The paper also offers some reflections on the relationship between the proposed process and existing approaches to Personas such as the data-driven and qualitative Personas. Moreover, the paper offers reflections on the capacity of LLMs to capture user behaviours and personality traits, from the underlying dataset of qualitative interviews used for the analysis.