Machine-learning prediction of accessible assessment-item quality¶
Research Method · All research methods
Evidence · 4 claims (4 for) · 2 studies (2 associational),q2· 0 of 2 report an effect size · 4 claims rest on one study
Description¶
The researchers introduced three word embedding methods and three classifiers as a toolkit for predicting item quality for accessible assessments. The brief states that "The researchers introduced three word embedding methods and three classifiers to predict item quality for accessible assessments." This toolkit operationalizes the study's goal of using AI to identify which math items work well for students with visual impairments who use screen readers, supporting a new way to present math content online.
Accounts¶
- Word embedding and classifier toolkit for predicting accessible math item quality: The researchers introduced three word embedding methods and three classifiers as a toolkit for predicting item quality for accessible assessments. The brief states that "The researchers introduced three word embedding methods and three classifiers to predict item quality for accessible assessments." This toolkit operationalizes the study's goal of using AI to identify which math items work well for students with visual impairments who use screen readers, supporting a new way to present math content online. (Kang Xue (2022))
Claims¶
- Three word embedding methods and three classifiers were introduced to predict item quality for accessible math assessments [+W]
- Math assessment items can be classified as high-quality or low-quality for students with visual impairments based on whether they measure achievement equally well for students with and without VI [+W]
- The item-quality and prediction work is part of a larger project aiming to make online math more accessible to students with visual impairments [+W]
- A random forest classified flagged versus non-flagged word problems with the best accuracy of five tested models (AUC = 0.75) [+W]
Related Research Methods¶
-
Key Sources¶
- Kang Xue, Elizabeth Barker. (2022). Using Artificial Intelligence (AI) to improve math accessibility for students with visual impairments. https://www.nwea.org/resources/using-artificial-intelligence-ai-to-improve-math-accessibility-for-students-with-visual-impairments/
Page metadata
| Field | Value |
|---|---|
type |
research-method |
id |
machine-learning-prediction-of-accessible-assessment-item-quality |
title |
Machine-learning prediction of accessible assessment-item quality |
description |
The researchers introduced three word embedding methods and three classifiers as a toolkit for predicting item quality for accessible assessments. |
status |
review |
moved_from |
element/word-embedding-classifier-toolkit-accessible-math-items |
generated |
by process:sweep-kinds on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — kang-xue-2022 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.