Claims

APTA's machine classifiers reached training-data accuracy of .81 for help type and .66 for conceptual content under 10-fold cross validation

Claim · All claims
Evidence · 1 study · causal r? · q2
Currency · newest study 2014 · not yet checked against its sources · not reviewed by a person
Design limits · Walker 2014: no comparison group (read from the study by two models, 2026-10-27)

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? A support vector machine classifier trained with chi-squared feature selection achieved .81 accuracy for help type and .66 for conceptual content on training data. → Walker 2014

Evidence

Walker 2014

Walker, E., Rummel, N., & Koedinger, K. R. (2014). Adaptive Intelligent Support to Improve Peer Tutoring in Algebra. Int J Artif Intell Educ 24, 33–61. https://doi.org/10.1007/s40593-013-0001-9

q2 · i? · causal · r?

Technical evaluation of APTA's dialogue classifiers built with Taghelper Tools, using unigrams, bigrams, line length, punctuation, and domain-context features. The article reports that "the classifier had an accuracy of .81 for help type and .66 for conceptual content" on training data.

"We used a chi-squared feature selection algorithm to rank the most predictive features, and 10-fold cross validation to train a support vector machine classifier for help type and conceptual content. On training data, the classifier had an accuracy of .81 for help type and .66 for conceptual content."

Discussion

Page metadata
Field Value
type claim
id apta-classifier-accuracy-help-type-conceptual
title APTA's machine classifiers reached training-data accuracy of .81 for help type and .66 for conceptual content under 10-fold cross validation
description APTA's machine classifiers reached training-data accuracy of .81 for help type and .66 for conceptual content under 10-fold cross validation
status review
evidence_strength moderate
newest_evidence 2014
generated by process:wiki-ingest on 2026-10-27
trust unverified — no one has confirmed this page's content
sources 1 — walker-2014

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