DKT+ knowledge states discriminate STEM from non-STEM students better than DKT knowledge states for the majority of mathematical skills.¶

Claim · All claims
Evidence · 1 study · associational r1 · q2
Currency · newest study 2018 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Independent sample t-tests per skill show the knowledge state extracted from DKT+ has a better discrimination power between STEM and non-STEM classes than DKT, with higher t-score magnitudes for the majority of skills. → Yeung 2018

Evidence¶

Yeung 2018¶

Yeung, C.-K., Lin, Z., Yang, K., & Yeung, D.-Y. (2018). Incorporating Features Learned by an Enhanced Deep Knowledge Tracing Model for STEM/Non-STEM Job Prediction. arXiv preprint arXiv:1806.03256. https://arxiv.org/abs/1806.03256

q2 · i? · associational · r1

Independent sample t-tests over each mathematical skill, visualized as a heatmap in Figure 3 (Section 5.2.2). The authors report that "the knowledge state extracted from the DKT+ has a better discrimination power between the STEM and the non-STEM classes" for the majority of skills.

"For majority of the skills, the independent sample t-tests show that the knowledge state extracted from the DKT+ has a better discrimination power between the STEM and the non-STEM classes, as their magnitudes of t-score are higher than those in the DKT."

Discussion¶

Related Claims¶

• Models trained with combined DKT/DKT+ knowledge-state and student-profile features generally outperform models trained with student profile alone on STEM/non-STEM job prediction. — related
• LDA projection visualizations show knowledge-state features separate STEM and non-STEM classes better than student-profile features. — related
• STEM students show a higher mastery level and a higher learning gain in mathematics than non-STEM students. — related