Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Creating Disability Story Videos with Generative AI: Motivation, Expression, and Sharing

Shuo Niu, Dylan Clements, Hyungsin Kim

TL;DR

This paper investigates how nine people with disabilities (PwD) used Generative AI (GenAI) to create disability-story videos, grounding the study in Lambert's digital storytelling theory. It introduces the Momentous Depiction framework, identifying four affordances—non-capturable depiction, identity concealment, contextual authenticity, and emotion articulation—that shape GenAI-assisted storytelling outcomes and reveal design gaps. Through a controlled creation flow (script generation, image/voiceover creation, and video assembly) and thematic analysis of prompts and interviews, the study shows GenAI can lower production barriers and enable expressive, advocacy-oriented narratives, while also introducing misrepresentations and coherence challenges. The findings offer design implications across story completion, identity-preserving formats, and imperfection correction, stressing user autonomy and localization to support authentic, accessible disability storytelling with GenAI.

Abstract

Generative AI (GenAI) is both promising and challenging in supporting people with disabilities (PwDs) in creating stories about disability. GenAI can reduce barriers to media production and inspire the creativity of PwDs, but it may also introduce biases and imperfections that hinder its adoption for personal expression. In this research, we examine how nine PwD from a disability advocacy group used GenAI to create videos sharing their disability experiences. Grounded in digital storytelling theory, we explore the motivations, expression, and sharing of PwD-created GenAI story videos. We conclude with a framework of momentous depiction, which highlights four core affordances of GenAI that either facilitate or require improvements to better support disability storytelling: non-capturable depiction, identity concealment and representation, contextual realism and consistency, and emotional articulation. Based on this framework, we further discuss design implications for GenAI in relation to story completion, media formats, and corrective mechanisms.

Creating Disability Story Videos with Generative AI: Motivation, Expression, and Sharing

TL;DR

This paper investigates how nine people with disabilities (PwD) used Generative AI (GenAI) to create disability-story videos, grounding the study in Lambert's digital storytelling theory. It introduces the Momentous Depiction framework, identifying four affordances—non-capturable depiction, identity concealment, contextual authenticity, and emotion articulation—that shape GenAI-assisted storytelling outcomes and reveal design gaps. Through a controlled creation flow (script generation, image/voiceover creation, and video assembly) and thematic analysis of prompts and interviews, the study shows GenAI can lower production barriers and enable expressive, advocacy-oriented narratives, while also introducing misrepresentations and coherence challenges. The findings offer design implications across story completion, identity-preserving formats, and imperfection correction, stressing user autonomy and localization to support authentic, accessible disability storytelling with GenAI.

Abstract

Generative AI (GenAI) is both promising and challenging in supporting people with disabilities (PwDs) in creating stories about disability. GenAI can reduce barriers to media production and inspire the creativity of PwDs, but it may also introduce biases and imperfections that hinder its adoption for personal expression. In this research, we examine how nine PwD from a disability advocacy group used GenAI to create videos sharing their disability experiences. Grounded in digital storytelling theory, we explore the motivations, expression, and sharing of PwD-created GenAI story videos. We conclude with a framework of momentous depiction, which highlights four core affordances of GenAI that either facilitate or require improvements to better support disability storytelling: non-capturable depiction, identity concealment and representation, contextual realism and consistency, and emotional articulation. Based on this framework, we further discuss design implications for GenAI in relation to story completion, media formats, and corrective mechanisms.
Paper Structure (38 sections, 11 figures, 1 table)

This paper contains 38 sections, 11 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Storytelling in Disability Research
  4. Generative AI for People With Disabilities
  5. Disability Storytelling through Video-Making
  6. Method
  7. Study Context
  8. Study Procedure
  9. Pre-study Session
  10. Creation Tasks
  11. Post-study Interview
  12. Data Analysis
  13. Results
  14. RQ1: Story Moments and Motivation
  15. Real-World Disability Challenges
  16. ...and 23 more sections

Figures (11)

  • Figure 1: An example YouTube Short video produced by [CAMPAIGN NAME] in 2024. The video features a campaign member narrating a historical story about how Justin Dart Jr. advocated for PwDs to avoid paying higher prices at gas stations, accompanied by five static historical images illustrating the narration.
  • Figure 2: Creation Task Flow
  • Figure 3: Stories created by each participant and example scenes. The captions under each image summarize the stories created by the participant.
  • Figure 4: Left: P5 requested ChatGPT to depict people laughing and drinking in the theater. Right: P5 requested ChatGPT to illustrate that the PwD had to leave the theater.
  • Figure 5: Left: ChatGPT created an scene of a PwD driving. Middle: In the next scene, ChatGPT changed the character's shirt color and added glasses. Right: P2 requested ChatGPT to restore the original shirt color and remove the glasses.
  • ...and 6 more figures