EUVIMEDEUVIMED entdecken
Crossref

Reliability by Design: Human–AI Writing Assessment

Ali Mikaeili

Peer Beyond Graduate Research Conference · 19.05.2026 · 2 (1)

DOI: 10.55016/tspy3m52 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Peer Beyond Graduate Research Conference, online erschienen am 19.05.2026. Verfasst von Ali Mikaeili.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-stakes writing assessment is a standards-referenced judgment practice in which reliability depends on shared interpretations of quality rather than mechanical measurement. This study examines reliability and standards communication in a rubric-driven, AI-supported system for Alberta English Language Arts 30–1. Fifteen publicly released exemplar essays (2022–2024) were evaluated using verbatim rubric embedding, criterion-level evidence requirements, and a gated decision process without numerical aggregation. Reliability was assessed through alignment with authorized classifications and stability across repeated evaluations (150 decisions). The system matched official classifications in 93.3% of cases and was fully stable across repetitions, with all disagreements confined to adjacent performance boundaries. Qualitative comparison of teacher and AI commentaries indicates that the system more consistently externalized criterion-referenced warrants, enhancing transparency without displacing human authority. Findings frame reliability as an emergent property of assessment-system design and position AI as infrastructure for contestable standards communication.

Zitieren

APA

Mikaeili, A. (2026). Reliability by Design: Human–AI Writing Assessment. Peer Beyond Graduate Research Conference, 2(1). https://doi.org/10.55016/tspy3m52

Vancouver

Mikaeili A. Reliability by Design: Human–AI Writing Assessment. Peer Beyond Graduate Research Conference. 2026;2(1). doi:10.55016/tspy3m52

BibTeX
@article{Mikaeili2026,
  author = {Mikaeili, Ali},
  title = {Reliability by Design: Human–AI Writing Assessment},
  journal = {Peer Beyond Graduate Research Conference},
  year = {2026},
  volume = {2},
  number = {1},
  doi = {10.55016/tspy3m52}
}
Kostenlos starten →