Flagged word problems were shorter (lower word count) but had more sentences than non-flagged problems in descriptive statistics¶
Claim · All claims
Evidence · 1 study · associationalr2·q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person · recheck by 2028: tool and model accuracy changes quickly
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? Descriptive means showed word count M = 82 for non-flagged vs M = 70 for flagged problems, and sentence count M = 5.5 for flagged vs M = 4.8 for non-flagged problems. → Kole Norberg 2025
Evidence¶
Kole Norberg 2025¶
Kole Norberg, Husni Almoubayyed, and Stephen Fancsali. (2025). Linguistic Features Predicting Math Word Problem Readability Among Less-Skilled Readers. Proceedings of the 18th International Conference on Educational Data Mining, Palermo, Italy. https://doi.org/10.5281/zenodo.15870274
q2 · i? · associational · r2
Descriptive statistics (Table A.1) comparing flagged and non-flagged problems on all metrics. The article notes these are mean differences only: "mean differences may mask more complex patterns in the data." No significance test or effect size is reported for these contrasts.
"others demonstrated larger differences, particularly in structural elements like word count ( M =82 for non-flagged problems vs. M =70 for flagged) and sentence count ( M =5.5 for flagged problems vs. M =4.8 for non-flagged problems."
Discussion¶
Related Claims¶
- A random forest classified flagged versus non-flagged word problems with the best accuracy of five tested models (AUC = 0.75) — related
- Partial dependence plots showed higher word count, more dependent clauses, and higher custom magnitude raised predicted flag probability, with non-linear relationships — related
- 4,446 of 9,421 MATHia word problems showed larger-than-expected error-rate gaps between less- and more-skilled readers and were flagged for potential readability concerns — related
- In the random forest, word count was the most important readability feature while traditional readability formulas ranked near the bottom — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
flagged-problems-shorter-more-sentences-descriptives |
title |
Flagged word problems were shorter (lower word count) but had more sentences than non-flagged problems in descriptive statistics |
description |
Flagged word problems were shorter (lower word count) but had more sentences than non-flagged problems in descriptive statistics |
status |
review |
evidence_strength |
weak |
newest_evidence |
2025 |
recheck_by |
2028 |
generated |
by process:wiki-ingest on 2026-10-08 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — kole-norberg-2025 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.