Multi-unidimensional approach to bridging psychometric and ITS learner models

Research Method · All research methods
Evidence · 1 claim (1 for) · 1 study (1 theoretical), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description

Siette addresses the mismatch between the fine-grained multidimensional learner models of ITSs and the single-latent-trait focus of CTT and IRT through a multi-unidimensional approach. Rather than using true multidimensional IRT models, the system "developed a mechanism that assumes that multiple independent traits are assessed simultaneously." This allows a CAT component to produce separate knowledge estimates for each domain topic in a hierarchical learner model, supporting adaptive question selection across multiple nodes. The domain model uses part-of relationships with topics and subtopics, and items can be attached to one or more sibling nodes.

Accounts

• Multi-unidimensional approach to bridging psychometric and ITS learner models: Siette addresses the mismatch between the fine-grained multidimensional learner models of ITSs and the single-latent-trait focus of CTT and IRT through a multi-unidimensional approach. Rather than using true multidimensional IRT models, the system "developed a mechanism that assumes that multiple independent traits are assessed simultaneously." This allows a CAT component to produce separate knowledge estimates for each domain topic in a hierarchical learner model, supporting adaptive question selection across multiple nodes. The domain model uses part-of relationships with topics and subtopics, and items can be attached to one or more sibling nodes. (Conejo et al. (2016))

Claims

• Multidimensional latent variable models rarely support more than about four to six latent variables, limiting fine-grained SKIVE modeling [+W]

Related Research Methods

-

Key Sources

• Conejo, R., Guzmán, E., & Trella, M. (2016). The SIETTE Automatic Assessment Environment. International Journal of Artificial Intelligence in Education, 26, 270–292. https://doi.org/10.1007/s40593-015-0078-4

Page metadata

Field	Value
type	research-method
id	multi-unidimensional-approach-to-bridging-psychometric-and-its-learner-models
title	Multi-unidimensional approach to bridging psychometric and ITS learner models
description	Siette addresses the mismatch between the fine-grained multidimensional learner models of ITSs and the single-latent-trait focus of CTT and IRT through a multi-unidimensional approach.
status	review
generated	by process:settle-candidates on 2026-10-28
trust	unverified — no one has confirmed this page's content

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