Of the student models surveyed from 2013-2014 AIED, EDM and ITS conferences, 53% have low or mid portability restrictions.¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2016 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? In the article's survey analysis, 34% of classified models have low restrictions, almost 19% medium restrictions, and 40% are hard or very hard to port, so 53% have low or mid restrictions. → Valdés Aguirre 2016

Evidence¶

Valdés Aguirre 2016¶

Valdés Aguirre, B., Ramírez Uresti, J. A., & du Boulay, B. (2016). An Analysis of Student Model Portability. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-016-0113-0

q2 · i? · design · r2

This is the article's analysis of its own graded survey of student models from AIED 2013, EDM 2014 and ITS 2014, presented with a histogram of models per portability-restriction class (Fig. 2). The authors state that "The fact that 53 % of the models have low or mid portability restrictions can be interpreted as half the models show promise to be ported".

"We observe that 34 % of the classified models have low restrictions, almost 19 % of them have medium restrictions, and 40 % the SM (24 % and 16 % respectively) are hard or very hard to port."

Discussion¶

Related Claims¶

• Accessibility and complexity dimensions show the lowest portability restrictions among surveyed student models, while popularity and architecture show the highest. — related
• Educational data mining keywords redistribute across new clusters over time, showing evolving specialization in AIED — related