Consistent student models reduce learning problems and raise average performance, supporting reuse of student models across courses¶

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? In simulations where the initial LSp was already consistent with the student's actual learning styles, fewer learning problems and greater average performance occurred, requiring fewer iterations to finish the course. → Fabiano Dorça 2015

Evidence¶

Fabiano Dorça 2015¶

Fabiano Dorça. (2015). Implementation and use of Simulated Students for Test and Validation of new Adaptive Educational Systems: a Practical Insight. Int J Artif Intell Educ. https://doi.org/10.1007/s40593-015-0037-0

q2 · i? · design · r2

Simulation experiment (strategy 3) initialized with LSp values consistent with the simulated student's actual learning styles, testing the maintenance aspect. Figures 6–8 show LSp remained consistent and performance graphs show "a lesser number of poor performances appeared in the figure."

"It is possible to notice that in this experiment we had less learning problems and greater average performance than in previous experiments. Consequently, a lesser number of iterations was necessary in order to finish the course."

Discussion¶

Related Claims¶

• Cold-start initialization converges faster than starting from an inconsistent student model — a narrower finding that bears on this claim
• Reinforcing learning styles absent from the selected combination on poor performance (strategy 3) yields the most consistent probabilistic learning-style model — related