📣 Help Shape the Future of UKRI's Gateway to Research (GtR)

We're improving UKRI's Gateway to Research and are seeking your input! If you would be interested in being interviewed about the improvements we're making and to have your say about how we can make GtR more user-friendly, impactful, and effective for the Research and Innovation community, please email gateway@ukri.org.

AI-Driven Conversational Storytelling with Humans in Natural Language

Lead Research Organisation: Edinburgh Napier University
Department Name: School of Eng and the Built Environment

Abstract

AI-Driven Conversational Storytelling with Humans in Natural Language - Storytelling has long been a central part of human society and entertainment and has taken many forms throughout history. However, traditional forms of storytelling often involve passive viewer experiences, and there is a growing demand for more interactive and engaging storytelling experiences. Interactivity is an essential part of the school and entertainment experience, but it must be carefully balanced with the integrity of the narrative. This is particularly important in the context of conversational AI and robotics, where excessive interaction can disrupt the story and insufficient interaction can lead to audience disengagement.
Narrative interaction is therefore a crucial issue in the field of conversational AI. However, achieving a balance between human-machine interaction and engaging narrative requires significant study, design and training efforts. In this project, I propose to explore the current state of the art in conversational storytelling, and machine/deep learning, and develop a new framework/model to support active learning capabilities through real-time telling and interpreting facts from different modes such as text-based data, images, video, and physical presentations. I will also examine the impact of multi-character dialogue on the audience. This knowledge has the potential to address one of the biggest challenges in conversational AI and human-machine interactions and provide a key solution for interactive and engaging narrative experiences [1].
This project also proposes the research then creation of a new framework for creating interactive narrative experiences that effectively engage and educate users in real-time by using a large language model (LLM) such as GPT-3 and computer vision techniques such as CNNs and LSTMs. The goal of this project is to create a responsive system that is capable of understanding and responding to user gestures and emotions in real-time in order to adapt the narrative. The system will be designed to be used in a variety of applications such as storytelling, education, and entertainment.

People

ORCID iD

Lewis Watson (Student)

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/W524578/1 30/09/2022 29/09/2028
2890967 Studentship EP/W524578/1 30/09/2023 29/09/2026 Lewis Watson