Machine-learning-based responder selection raises mean group reading-speed gain from 23% to 43%¶

Claim · All claims
Evidence · 1 study · causal r2 · q3
Currency · newest study 2024 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Applying the diagnostic to select responders (predicted gain ≥ 13.5%) increased mean reading-speed gain at group level from 23% in the unselected group to 43% in the machine-selected group. → Benjamin Gagl & Klara Gregorová 2024

Evidence¶

Benjamin Gagl & Klara Gregorová 2024¶

Benjamin Gagl & Klara Gregorová. (2024). Investigating lexical categorization in reading based on joint diagnostic and training approaches for language learners. npj Science of Learning 9:29. https://doi.org/10.1038/s41539-024-00237-7

q3 · i? · causal · r2

Categorization diagnostics on leave-one-out cross-validation used an optimized decision boundary of 13.5% predicted reading-speed increase, with sensitivity 0.73, specificity 0.74, accuracy 0.73, and precision 0.86 (N = 44 of 75 selected; 38 true positives, 6 false positives, 17 true negatives, 14 false negatives). The selected group's mean gain was significantly higher, t = 2.188.

"Therefore, the selection of responders increased the mean reading speed from 23% to 43% on the group level (FE = 0.199, SE = 0.091, t = 2.188, see Fig. 5C)."

Discussion¶

Related Claims¶

• An individualized machine-learning diagnostic using LCM-based features predicts lexical categorization training benefits with moderate-to-good accuracy — related
• K-Means clustering of LIME feature-importance profiles identifies 2 responder and 4 non-responder subgroups within binary intervention-response classes — a narrower finding that bears on this claim