Can AI Have a Personality? Prompt Engineering for AI Personality Simulation: A Chatbot Case Study in Gender-Affirming Voice Therapy Training

TL;DR

This work investigates whether large language models can be steered to exhibit a stable, predefined personality through prompt engineering in a gender-affirming voice therapy training chatbot. Monae Jackson serves as a detailed persona embedded via structured prompts and background information, with personality assessed using the Big Five and a Jungian-type MBTI framework across independent sessions. Results indicate strong cross-framework agreement on traits such as emotional sensitivity, openness, introversion, and interpersonal warmth, alongside emergent traits like messiness and artistic interest, suggesting that carefully designed prompts can yield psychologically plausible AI personas. The findings support the potential of AI personas to augment SLP education and therapeutic training, while underscoring ethical, memory-related, and generalizability considerations that must be addressed in future research and deployment.

Abstract

This thesis investigates whether large language models (LLMs) can be guided to simulate a consistent personality through prompt engineering. The study explores this concept within the context of a chatbot designed for Speech-Language Pathology (SLP) student training, specifically focused on gender-affirming voice therapy. The chatbot, named Monae Jackson, was created to represent a 32-year-old transgender woman and engage in conversations simulating client-therapist interactions. Findings suggest that with prompt engineering, the chatbot maintained a recognizable and consistent persona and had a distinct personality based on the Big Five Personality test. These results support the idea that prompt engineering can be used to simulate stable personality characteristics in AI chatbots.