Chatbots With Attitude

Abstract

Equipping chatbots with personality has the potential of transforming user interactions from mere transactions to engaging conversations, enhancing user satisfaction and engagement. In this work, we infuse chatbot personalities by dynamically adapting chatbot responses using GPT-4 based on a dedicated chatbot personality model. This novel intermediate stage between the chatbot and the user allows to adjust the chatbot’s response without altering the chatbot’s semantic capabilities. To test the effectiveness of our personality infusion, we first collected human-chatbot conversations from 33 participants while they interacted with three LLM-based chatbots (GPT-3.5, Llama-2 13B, and Mistral 7B). Then, we conducted an online rating survey with 725 participants on the collected conversations. We analyze the impact of the personality infusion on the perceived trustworthiness of the chatbots and the suitability of different personality profiles for real-world chatbot use cases. Our work paves the way for dynamic, personalized chatbots, enhancing user trust and real-world applicability.