Apprentice learner models are domain-general: they learn expert models across eight tutor domains without specialized domain knowledge¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2022 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? The Decision Tree and Trestle models learn expert models for seven additional tutoring systems teaching a wide range of knowledge types across multiple domains. → Christopher J. MacLellan & Kenneth R. Koedinger 2022

Evidence¶

Christopher J. MacLellan & Kenneth R. Koedinger 2022¶

Christopher J. MacLellan & Kenneth R. Koedinger. (2022). Domain-General Tutor Authoring with Apprentice Learner Models. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-020-00214-2

q2 · i? · design · r2

A cross-domain analysis evaluated both apprentice learner models across seven additional tutoring domains beyond experimental design, comparing them to Example-Tracing and human learners. Both models learned across a wide range of tutors and domains without additional specialized domain knowledge.

"show that they are capable of learning an expert model for seven additional tutoring systems that teach a wide range of knowledge types (associations, categories, and skills) across multiple domains (language, math, engineering, and science)"

Discussion¶

Related Claims¶

• Apprentice learner models act as a check against expert blind spots because they start without target skills — related
• Apprentice learner models support efficient tutor authoring, more efficient than Example-Tracing with mass production — related
• Meta-analytic evidence indicates intelligent tutoring systems yield positive learning outcomes compared with non-ITS conditions — related
• Intelligent tutoring systems are reported to improve learning outcomes, especially in structured knowledge domains — related