Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Persona-L has Entered the Chat: Leveraging LLM and Ability-based Framework for Personas of People with Complex Needs

Lipeipei Sun, Tianzi Qin, Anran Hu, Jiale Zhang, Shuojia Lin, Jianyan Chen, Mona Ali, Mirjana Prpa

TL;DR

The findings indicate the potential of Persona-L to increase empathy and understanding of complex needs while also revealing the need for transparency of data used in persona creation, the role of the language and tone, and the need to provide a more balanced presentation of abilities with constraints.

Abstract

We present Persona-L, a novel approach for creating personas using Large Language Models (LLMs) and an ability-based framework, specifically designed to improve the representation of users with complex needs. Traditional methods of persona creation often fall short of accurately depicting the dynamic and diverse nature of complex needs, resulting in oversimplified or stereotypical profiles. Persona-L enables users to create and interact with personas through a chat interface. Persona-L was evaluated through interviews with UX designers (N=6), where we examined its effectiveness in reflecting the complexities of lived experiences of people with complex needs. We report our findings that indicate the potential of Persona-L to increase empathy and understanding of complex needs while also revealing the need for transparency of data used in persona creation, the role of the language and tone, and the need to provide a more balanced presentation of abilities with constraints.

Persona-L has Entered the Chat: Leveraging LLM and Ability-based Framework for Personas of People with Complex Needs

TL;DR

The findings indicate the potential of Persona-L to increase empathy and understanding of complex needs while also revealing the need for transparency of data used in persona creation, the role of the language and tone, and the need to provide a more balanced presentation of abilities with constraints.

Abstract

We present Persona-L, a novel approach for creating personas using Large Language Models (LLMs) and an ability-based framework, specifically designed to improve the representation of users with complex needs. Traditional methods of persona creation often fall short of accurately depicting the dynamic and diverse nature of complex needs, resulting in oversimplified or stereotypical profiles. Persona-L enables users to create and interact with personas through a chat interface. Persona-L was evaluated through interviews with UX designers (N=6), where we examined its effectiveness in reflecting the complexities of lived experiences of people with complex needs. We report our findings that indicate the potential of Persona-L to increase empathy and understanding of complex needs while also revealing the need for transparency of data used in persona creation, the role of the language and tone, and the need to provide a more balanced presentation of abilities with constraints.
Paper Structure (61 sections, 6 figures, 8 tables)

This paper contains 61 sections, 6 figures, 8 tables.

Table of Contents

  1. Abstract
  2. Author Keywords
  3. Introduction
  4. Related Work
  5. Approaches for Creating Personas
  6. Data-driven Personas
  7. LLM -Generated Personas
  8. Challenges and Limitations in Personas
  9. Developing Personas representing People with Complex Needs
  10. Implications for Interactive and Dynamic User Interface for LLM-generated Personas
  11. Positioning of Our Research in the Context of Related Work
  12. Persona-L System Design
  13. An Ability-Based Framework for LLM persona
  14. User Interface Design
  15. Phase 1: Profile Phase
  16. ...and 46 more sections

Figures (6)

  • Figure 1: Persona-L Interface featuring a chat window where users can interact with created Persona-L: Erica about previously selected Theme: Employment.
  • Figure 2: System Design Diagram. It maps the journey from data collection to interactive persona creation, highlighting the collaborative efforts required to deliver a sophisticated and engaging user experience.
  • Figure 3: Phases in User Interface Design: The "Profile Phase" involves persona customization and theme selection. The "Ability Phase" allows users to explore and select key abilities under a specific theme. The "Interaction Phase" facilitates user engagement with the personas LLMs and provides tools for saving and documenting interactions.
  • Figure 4: Profile Phase Page
  • Figure 5: Persona-L: Display of Abilities per selected Theme:Employment
  • ...and 1 more figures