Adults with low literacy using AutoTutor fall into four behavioral clusters: higher performers, conscientious readers, under-engaged readers, and struggling readers¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2021 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Cluster analysis of AutoTutor accuracy and response time data identified four distinct behavioral profiles among 252 adults with low literacy. → Fang 2021

Evidence¶

Fang 2021¶

Fang, Y., Lippert, A., Cai, Z., Chen, S., Frijters, J. C., Greenberg, D., & Graesser, A. C. (2021). Patterns of Adults with Low Literacy Skills Interacting with an Intelligent Tutoring System. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-021-00266-y

q2 · i? · associational · r2

Clustering analysis of log-file data from 252 adults in a blended reading intervention. Hierarchical clustering using Ward's method outperformed k-means on connectivity, Silhouette Width, and Dunn Index, yielding a "four categories" solution selected as locally optimum.

"The adults’ average accuracy and response time in AutoTutor were used to cluster the adults into four categories: higher performers (comparatively fast and accurate), conscientious readers (slow but accurate), under-engaged readers (fast at the expense of somewhat lower accuracy) and struggling readers (slow and inaccurate)."

Discussion¶

Related Claims¶

• Cluster membership moderated the relationship between theoretical comprehension level and both response time and accuracy in AutoTutor — related
• Struggling readers were slow and inaccurate, with the lowest accuracy across all theoretical levels — a narrower finding that bears on this claim
• Higher performers outperformed struggling readers on posttest comprehension after controlling for pretest, on both WJ-III and RAPID measures — a narrower finding that bears on this claim
• Under-engaged readers answered quickly but with lower accuracy, performing worst on word-level lessons — a narrower finding that bears on this claim