FIMA-light automatically builds goal-decomposition trees from teachers' lesson plans with about 90% accuracy of estimated hidden sub-goals¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2015 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? FIMA-light, a rule-based intelligent front-end to SMARTIES, generates plausible goal-decomposition trees from rough lesson-plan input with about 90% accuracy in estimating hidden sub-goals. → Mizoguchi 2015

Evidence¶

Mizoguchi 2015¶

Mizoguchi, R., & Bourdeau, J. (2015). Using Ontological Engineering to Overcome AI-ED Problems: Contribution, Impact and Perspectives. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-015-0077-5

q2 · i? · design · r2

The article reports performance of FIMA-light, which maps teacher-friendly lesson-plan vocabulary to OMNIBUS terms and generates decomposition trees. The 90% figure is the article's own reported accuracy of estimation; no effect size or comparative test is printed. The system was assessed using lesson plans of five subjects by four junior high school teachers.

"FIMA-light can generate trees that have about 90 % accuracy of estimation of hidden sub-goals and can give authors opportunities to reflect their design rationale left implicit in the initial lesson plan"

Discussion¶

Related Claims¶

• OMNIBUS/SMARTIES is, to the authors' knowledge, the only authoring system that does not favor one learning/instructional theory over another — related
• Teachers treated AI as a provisional thinking partner whose outputs required iterative adaptation rather than automatic adoption — related