Skip to content

The diagnostic-review mechanism: AI issue-level diagnosis passing through student interpretation, revision, teacher review, and reflection

Design · All designs
Evidence · 2 claims (2 for) · 2 studies (2 causal), q2 · 1 of 2 report an effect size · 1 claim rests on one study

Description

The article proposes a classroom sequence in which AI diagnostic feedback becomes formative only through downstream activity. "The classroom sequence was task submission, AI diagnosis, student interpretation, independent revision, structured teacher review, reassessment, and reflection." The framework integrates formative assessment, feedback literacy, self-regulated learning, and teacher-feedback research, ordered by how diagnostic information moves through interpretation, revision, reassessment, and reflection. Teacher review comprises "confirmation, correction, supplementation, and re-explanation of AI feedback", connecting automated evidence with situated writing judgment and making review workload observable.

Design Implications

Context

Requirements

  • Issue-level AI diagnosis that separates problem diagnosis from revision suggestions and does not rewrite the composition
  • Structured student interpretation before revision (restating problems, explaining effects, identifying uncertainties, specifying a revision plan)
  • Structured teacher review after revision, followed by reassessment and reflection

Constraints

  • Evidence comes from two intact classes taught by one instructor, leaving class selection and instructor effects in the observed group contrast
  • Student time-on-task was not recorded, and the contrast may include additional interpretation, reflection, and revision time
  • Cycle order coincided with task type, and no delayed post-test was administered

Target Learners

  • University EFL students in English writing courses

Learning Goals

  • L2 writing quality and revision skill
  • Feedback literacy and self-assessment accuracy
  • Self-regulated revision behavior

Claims

Examples

-

Key Sources

  • Yao X-C and Fan L (2026) From automated scoring to learning diagnosis: a mechanism study of AI-supported formative assessment in English writing. Front. Psychol. 17:1905455. https://doi.org/10.3389/fpsyg.2026.1905455
Page metadata
Field Value
type design
id diagnostic-review-mechanism-ai-formative-assessment
title The diagnostic-review mechanism: AI issue-level diagnosis passing through student interpretation, revision, teacher review, and reflection
description The article proposes a classroom sequence in which AI diagnostic feedback becomes formative only through downstream activity.
status review
generated by process:settle-candidates on 2026-10-10
trust unverified — no one has confirmed this page's content
sources 1 — yao-x-c-and-fan-l-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.