This academic article presents a study on the development of engaging and believable Social Chatbots (SCs) integrated with storytelling and Large Language Models (LLMs) in community settings. The study introduces Storytelling Social Chatbots (SSCs) which use story engineering to transform fictional game characters into live social entities within player communities. The process of story engineering includes character creation, live story presentation, and communication with community members. Utilising the LLM GPT-3, the authors developed SSC prototypes and evaluated their performance in an online gaming community. The results reveal that storytelling significantly enhances the engagement and believability of SCs in community settings.
Publication date: 2023
Project Page: ?
Paper: https://arxiv.org/pdf/2309.11478
