MétaCan
Menu
Back to cohort
Record W2562551526 · doi:10.1111/emip.12129

A Process for Reviewing and Evaluating Generated Test Items

2016· article· en· W2562551526 on OpenAlexaff
Mark J. Gierl, Hollis Lai

Bibliographic record

VenueEducational Measurement Issues and Practice · 2016
Typearticle
Languageen
FieldComputer Science
TopicIntelligent Tutoring Systems and Adaptive Learning
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsComputer scienceTest (biology)Process (computing)Subject-matter expertQuality (philosophy)Domain (mathematical analysis)Computerized adaptive testingItem bankItem response theoryData scienceArtificial intelligencePsychometricsExpert systemMathematicsStatisticsProgramming language

Abstract

fetched live from OpenAlex

Testing organization needs large numbers of high‐quality items due to the proliferation of alternative test administration methods and modern test designs. But the current demand for items far exceeds the supply. Test items, as they are currently written, evoke a process that is both time‐consuming and expensive because each item is written, edited, and reviewed by a subject‐matter expert. One promising approach that may address this challenge is with automatic item generation. Automatic item generation combines cognitive and psychometric modeling practices to guide the production of items that are generated with the aid of computer technology. The purpose of this study is to describe and illustrate a process that can be used to review and evaluate the quality of the generated item by focusing on the content and logic specified within the item generation procedure. We illustrate our process using an item development example from mathematics drawn from the Common Core State Standards and from surgical education drawn from the health sciences domain.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.131
metaresearch head score (Gemma)0.338
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.131
Threshold uncertainty score0.692

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.1310.338
Meta-epidemiology (narrow)0.0030.002
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0130.005
Science and technology studies0.0050.003
Scholarly communication0.0060.005
Open science0.0050.005
Research integrity0.0030.004
Insufficient payload (model declined to judge)0.0100.013

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.246
GPT teacher head0.429
Teacher spread0.183 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations19
Published2016
Admission routes1
Has abstractyes

Explore more

Same venueEducational Measurement Issues and PracticeSame topicIntelligent Tutoring Systems and Adaptive LearningFrench-language works237,207