Abrupt location or character changes mid-scenario co-occur with the lowest story-content coherence ratings¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2026 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? Sessions with abrupt location or character changes without narrative bridge coincided with the lowest coherence scores in the sample (≤ 1.75). → F. Rogosch 2026
Evidence¶
F. Rogosch 2026¶
F. Rogosch, A. Schrader. (2026). AI-Generated Interactive Fiction for Educational Use: A Pilot Study of Perceived Comprehensibility, Coherence, and Engagement. Proceedings of EDULEARN26 Conference. https://doi.org/10.21125/edulearn.2026.1075
q2 · i? · design · r2
Qualitative finding from the pilot's thematic analysis: two of ten free-text responses reported abrupt setting changes, exemplified by a participant quote about being teleported from a museum to a radio station, "co-occurring with the lowest coherence scores in the sample (≤ 1.75)".
"A second, more severe cluster (Theme 3, two responses) involves abrupt location or character changes mid-scenario ("Suddenly we were teleported from a museum to a radio station, with new characters praising me who had not been there before."), co-occurring with the lowest coherence scores in the sample (≤ 1.75)."
Discussion¶
Related Claims¶
- Story-content coherence is the weakest perceived-quality dimension of AI-generated educational interactive fiction in this pilot — related
- Narrative memory is superior when content follows stereotypical story grammar structure, and goal information is critical to comprehension — a broader claim this one bears on
- In a small pilot of one AI pipeline's educational interactive fiction, the dominant free-text criticism was the artificial in-fiction motivation for quiz prompts — related
- Participants liked the co-created stories (mean likability 8.61) and perceived them as coherent (mean coherence 8.28) on a 1-10 scale — related
- Self-reported perceived quality is largely decoupled from quiz performance in AI-generated educational interactive fiction — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
abrupt-setting-changes-lowest-coherence |
title |
Abrupt location or character changes mid-scenario co-occur with the lowest story-content coherence ratings |
description |
Abrupt location or character changes mid-scenario co-occur with the lowest story-content coherence ratings |
status |
review |
evidence_strength |
weak |
newest_evidence |
2026 |
source_checked |
2026-10-20 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — f-rogosch-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.