The survey reports, citing Qiu et al., that BKT consistently overestimates the accuracy of students' answers when a day or more has elapsed since their previous responses.¶

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

Subclaims¶

q2 i? The review attributes to Qiu et al. the finding that BKT overestimates answer accuracy after a gap of a day or more. → Shuanghong Shen 2021

Evidence¶

Shuanghong Shen 2021¶

Shuanghong Shen, Qi Liu, Zhenya Huang, Yonghe Zheng, Minghao Yin, Minjuan Wang, and Enhong Chen. (2021). A Survey of Knowledge Tracing: Models, Variants, and Applications. https://arxiv.org/abs/2105.15106 doi:10.48550/arxiv.2105.15106

q2 · i? · review · r2

Narrative review attributing this to Qiu et al., who "discover that BKT consistently overestimates the accuracy of students’ answers when a day or more had elapsed"; the survey explains BKT assumes performance stays the same regardless of elapsed time, motivating the BKT-Forget model.

"Qiu et al. [88] discover that BKT consistently overestimates the accuracy of students’ answers when a day or more had elapsed since their previous responses."

Discussion¶

Related Claims¶

• The survey reports, citing Pavlik et al., that no single knowledge tracing model was always the best, and that a better model must consider multiple student features and the learning context. — the general claim this finding bears on, with the studies behind it

• The survey states that deep learning knowledge tracing models exhibit superior performance to Bayesian and logistic models but have significant room for improvement in interpretability. — the general claim this finding bears on, with the studies behind it

• MS-BKT mastery estimates fluctuate less than classic BKT and avoid over-high estimates after long incorrect runs, in fictitious-student comparisons — related
• The survey reports, citing Lee and Brunskill, that individualized BKT in an intelligent tutoring system reduced by about half the questions required for 20% of students to achieve mastery. — related
• The survey reports, citing Desmarais and Baker, that students using the BKT-sequence recommendation algorithm solved more difficult exercises, obtained higher performance and spent more time in the system than students using the traditional approach. — related