Modular spreadsheet-based grading setup combining clustering, sampled manual grading, classification, and full review¶

Design · All designs
Evidence · 2 claims (2 for) · 1 study (1 design), q2 · 0 of 1 report an effect size · 2 claims rest on one study

Description¶

A reusable grading workflow in which student answers are clustered (k-means on lemmatized unigrams), a sample is manually graded as training data, per-question classifiers score the remaining answers, and all scores are reviewed in cluster order. The authors propose "a modular and reusable grading setup that can be used in a course setting without the need for specifically developed interfaces for grading"; a spreadsheet program displayed answers, scores, and comments.

Design Implications¶

Context¶

Requirements¶

Clustering must allow manually setting the number of clusters and provide a measure of representativeness for selecting training answers

Constraints¶

Evaluated on short answers (average 13 tokens) from one introductory computer science exam, mainly in Swedish

Target Learners¶

higher education students in comparatively large courses

Learning Goals¶

efficient and correct grading of short-answer exam questions

Claims¶

Examples¶

-

Key Sources¶

Rebecka Weegar · Peter Idestam-Almquist. (2024). Reducing Workload in Short Answer Grading Using Machine Learning. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-022-00322-1

Page metadata

Field	Value
`type`	`design`
`id`	`spreadsheet-cluster-grading-setup`
`title`	`Modular spreadsheet-based grading setup combining clustering, sampled manual grading, classification, and full review`
`description`	`A reusable grading workflow in which student answers are clustered (k-means on lemmatized unigrams), a sample is manually graded as training data, per-question classifiers score the remaining answers, and all scores a...`
`status`	`review`
`generated`	by `process:settle-candidates` on `2026-10-27`
`trust`	unverified — no one has confirmed this page's content
`sources`	1 — `rebecka-weegar-peter-idestam-almquist-2024`

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