ai
AI-Generated Interactive Fiction for Educational Use: A Pilot Study of Perceived Comprehensibility, Coherence, and Engagement
- Source
- arXiv — Computers and Society
- Published
- Last verified
- 12 Aug 2026
- Confidence
- Moderate
- Evidence
- Original document retained
- Reading time
- 1 min
- Country
- International
- Relevant to
- Research & Evidence, Technology & Data
Executive summary
What happened, and why should leadership care?
A pilot study explored the perceived effectiveness of AI-generated interactive fiction (IF) for higher education. The research aimed to assess narrative clarity, story-content coherence, engagement, and length acceptance of AI-generated educational content among STEM higher-education participants. While generative AI can produce educational content at scale, its practical utility hinges on its comprehensibility, narrative consistency, and ability to engage users.
Why this matters
Why is this strategically important?
The ability to generate high-quality, engaging educational content at scale using AI presents a significant strategic opportunity for workforce development and organizational learning. Ensuring that this AI-generated content is coherent, comprehensible, and engaging is critical for its effective adoption and to realize the full potential of AI in educational settings.
Key insights
What should be noted from the evidence?
- Generative AI has the potential to produce educational content at scale, including interactive and narrative learning experiences.
- The technical generation of educational content is insufficient; practical utility requires scenarios to be clear, consistent, and engaging.
- A pilot study evaluated AI-generated interactive fiction for educational use in higher education, specifically focusing on STEM content.
- Participants (N=22, STEM higher-education) rated AI-generated episodes on narrative clarity, story-content coherence, engagement, and length acceptance.
Evidence and confidence
How far can this assessment be trusted?
Moderate confidence. Provenance established; supporting evidence remains partial.
Analysis is prepared editorially by Aziz Shuaib Ausi. The original publication remains the authoritative record, and executive judgement remains entirely human.
Source
Where does this originate?
Reported by arXiv — Computers and Society · International. This briefing summarises the publication for executive use; the document itself is not reproduced here.
Read the original publication