Semi-supervised ANN framework combining ANNs with DINA and DINO diagnostic classification models

Research Method · All research methods
Evidence · 3 claims (1 for, 2 mixed) · 1 study (1 design), q1 · 0 of 1 report an effect size · 3 claims rest on one study

Description

The article proposes a framework that combines artificial neural networks with two typical theoretical diagnostic classification models, the DINA model and the DINO model, within a semi-supervised learning framework. Its purpose is to convert a pattern of item responses into a diagnostic classification robustly and accurately, addressing instability the authors attribute to earlier ANN approaches. The authors state this is "the first time of applying the thinking of semi-supervised learning into CDM".

Accounts

• Semi-supervised ANN framework combining ANNs with DINA and DINO diagnostic classification models: The article proposes a framework that combines artificial neural networks with two typical theoretical diagnostic classification models, the DINA model and the DINO model, within a semi-supervised learning framework. Its purpose is to convert a pattern of item responses into a diagnostic classification robustly and accurately, addressing instability the authors attribute to earlier ANN approaches. The authors state this is "the first time of applying the thinking of semi-supervised learning into CDM". (Kang Xue (2021))

Claims

• A semi-supervised ANN method combining DINA and DINO achieves appreciated classification performance across test conditions, especially when diagnostic quality is not high or the Q-matrix contains misspecified elements [+M]
• Prior ANN approaches to diagnostic classification produced unstable and unappreciated estimation unless great care was taken [~W]
• Misspecification of theoretical diagnostic classification models and inaccurate Q-matrices impact classification accuracy [~W]

Related Research Methods

-

Key Sources

• Kang Xue, Laine Bradshaw. (2021). A semi-supervised learning-based diagnostic classification method using artificial neural networks. Frontiers in Psychology, 11, 3992. https://www.frontiersin.org/journals/psychology

Page metadata

Field	Value
type	research-method
id	semi-supervised-ann-framework-combining-anns-with-dina-and-dino-diagnostic-classification
title	Semi-supervised ANN framework combining ANNs with DINA and DINO diagnostic classification models
description	The article proposes a framework that combines artificial neural networks with two typical theoretical diagnostic classification models, the DINA model and the DINO model, within a semi-supervised learning framework.
status	review
moved_from	theory/semi-supervised-ann-cdm-framework
generated	by process:sweep-kinds on 2026-10-10
trust	unverified — no one has confirmed this page's content
sources	1 — kang-xue-2021

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