Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SARD: A Human-AI Collaborative Story Generation

Ahmed Y. Radwan, Khaled M. Alasmari, Omar A. Abdulbagi, Emad A. Alghamdi

TL;DR

An evaluation of the usability of SARD and its creativity support shows that while node-based visualization of the narrative may help writers build a mental model, it exerts unnecessary mental overhead to the writer and becomes a source of distraction as the story becomes more elaborated.

Abstract

Generative artificial intelligence (GenAI) has ushered in a new era for storytellers, providing a powerful tool to ignite creativity and explore uncharted narrative territories. As technology continues to advance, the synergy between human creativity and AI-generated content holds the potential to redefine the landscape of storytelling. In this work, we propose SARD, a drag-and-drop visual interface for generating a multi-chapter story using large language models. Our evaluation of the usability of SARD and its creativity support shows that while node-based visualization of the narrative may help writers build a mental model, it exerts unnecessary mental overhead to the writer and becomes a source of distraction as the story becomes more elaborated. We also found that AI generates stories that are less lexically diverse, irrespective of the complexity of the story. We identified some patterns and limitations of our tool that can guide the development of future human-AI co-writing tools.

SARD: A Human-AI Collaborative Story Generation

TL;DR

An evaluation of the usability of SARD and its creativity support shows that while node-based visualization of the narrative may help writers build a mental model, it exerts unnecessary mental overhead to the writer and becomes a source of distraction as the story becomes more elaborated.

Abstract

Generative artificial intelligence (GenAI) has ushered in a new era for storytellers, providing a powerful tool to ignite creativity and explore uncharted narrative territories. As technology continues to advance, the synergy between human creativity and AI-generated content holds the potential to redefine the landscape of storytelling. In this work, we propose SARD, a drag-and-drop visual interface for generating a multi-chapter story using large language models. Our evaluation of the usability of SARD and its creativity support shows that while node-based visualization of the narrative may help writers build a mental model, it exerts unnecessary mental overhead to the writer and becomes a source of distraction as the story becomes more elaborated. We also found that AI generates stories that are less lexically diverse, irrespective of the complexity of the story. We identified some patterns and limitations of our tool that can guide the development of future human-AI co-writing tools.
Paper Structure (24 sections, 2 figures, 1 table)

This paper contains 24 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Generative AI for Story Creation
  4. AI-Authoring Tools
  5. AI Content Quality and Novelty
  6. System Overview
  7. Prompt Designing
  8. Canvas
  9. Setting Genre and Structure
  10. Adding Characters, Events and Actions
  11. Ordering of Events
  12. Methodology
  13. Study 1: Evaluating The usability and collaborative aspects of SARD
  14. Participants
  15. Task and Procedure
  16. ...and 9 more sections

Figures (2)

  • Figure 1: SARD: Novel generation through interactive storyboard. The user starts with (1) where the user sets the story structure and genre. (2) is where the user can create and add elements, either character, action, or relationship, to their storyboard. (2) can also be used to navigate through different storyboards and set the setting with an image. When creating an element the user drags it into the canvas (3) where it is translated into a node. The user can click the green button to represent character nodes with images, and then preview them with the blue button. This node can be connected to other elements creating relationships. After the user orders events (4), they can generate their storyboards into a story (5) which is displayed in the story tab.
  • Figure 2: Results from Study 1: (a) SUS Scores, (b) MICSI Sub-Scale Scores, (c) Exploratory Question Responses.