Topic-preference features separate grade groups better than Reading Time in all analyzed cases¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? In the Basic Separability Analysis on course A-2019, the best topic's Fisher's Discriminant Ratio exceeded that of Reading Time in every grade-group comparison considered (e.g., FDR 5.58 versus 0.05 for A-B in week 2 out-class). → Erwin Daniel López Zapata 2025

Evidence¶

Erwin Daniel López Zapata 2025¶

Erwin Daniel López Zapata, Cheng Tang, Valdemar Švábenský, Fumiya Okubo, Atsushi Shimada. (2025). LECTOR: Summarizing E-book Reading Content for Personalized Student Support. Int J Artif Intell Educ 35. https://doi.org/10.1007/s40593-025-00478-6

q2 · i? · design · r2

Feature-level separability analysis using Fisher's Discriminant Ratio on course A-2019 logs, comparing grade groups (A-B, B-C, C-D, D-F, at-risk) across weeks 1-4; "we identified a topic (B_Topic) that achieved a higher FDR than the Reading Time feature" in all cases.

"In all cases considered, we identified a topic (B_Topic) that achieved a higher FDR than the Reading Time feature."

Discussion¶

Related Claims¶

• LDA projection visualizations show knowledge-state features separate STEM and non-STEM classes better than student-profile features. — related
• Integrating LECTOR topic preferences into at-risk prediction shows a tendency to improve performance, with significant AUC gains only in some cases — related