The six clusters differ substantially in academic performance: Final Grade ANOVA η² = 0.770, with C0 exceeding C1 by 40.17 exam-score points¶

Claim · All claims
Evidence · 1 study (2 entries) · associational r1 · q2 · i3 large
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i3 Cluster membership is strongly associated with Final Grade (F(5, 13,997) = 9365.49, p < 0.001, η² = 0.770), with Exam Score as a sensitivity analysis (η² = 0.709). → Najem 2026 q2 i? Tukey HSD tests show the highest-performing cluster C0 exceeded the lowest-performing cluster C1 by a mean of 40.17 points (95% CI [39.55, 40.78], p < 0.001), and C5 exceeded C1 by 32.82 points. → Najem 2026 (2)

Evidence¶

Najem 2026¶

Najem, K., Zaoui Seghroucheni, Y., & Ziti, S. (2026). Behavioral clustering for adaptive learning object recommendation in higher education using learning analytics for personalized student success. Discover Education. https://doi.org/10.1007/s44217-026-02181-7

q2 · i3 · associational · r1

One-way ANOVA on the 14,003-record dataset comparing the six clusters on Final Grade, with Exam Score as a sensitivity analysis because the two outcomes are not statistically independent; the article reports η² = 0.770 and η² = 0.709 respectively.

"Therefore, the primary validation relies on Final Grade, F(5, 13,997) = 9365.49, p < 0.001, η2 = 0.770. Exam Score is reported as a sensitivity analysis (F(5, 13,997) = 6822.77, p < 0.001, η2 = 0.709)"

Najem 2026 (2)¶

Najem, K., Zaoui Seghroucheni, Y., & Ziti, S. (2026). Behavioral clustering for adaptive learning object recommendation in higher education using learning analytics for personalized student success. Discover Education. https://doi.org/10.1007/s44217-026-02181-7

q2 · i? · associational · r1

Post hoc Tukey HSD pairwise comparisons across the six clusters; C0 exceeded C1 by 40.17 points and C5 exceeded C1 by 32.82 points, with all top-versus-bottom pairwise comparisons significant at p < 0.001.

"Post hoc Tukey HSD comparisons revealed that the highest-performing cluster, C0 (Highly Engaged Achievers), differed significantly from the lowest-performing cluster, C1 (At-Risk Learners), by a mean of 40.17 points (95% CI [39.55, 40.78], p < 0.001)."

Discussion¶

Related Claims¶

• K-means clustering of standardized prior knowledge and final grades yields four performance profiles: Consistent Achievers, Growing Achievers, Declining Performers, and Struggling Performers — related
• Profiles differ in self-perceived academic skills: Engaged and Literate users report the highest problem-solving and cognitive endurance gains, while Uncritical Reliant users report the highest independent thinking — related
• Growing Achievers used StatBot significantly more than Declining Performers, driven mainly by initiating new inquiries — related
• Student academic ability varied across quarters but not systematically with changes in course structure — related
• The four exam-performance quartile groups differed significantly on first-unit exam scores, validating the grouping used for behavioral comparisons — related
• Fall clusters of coding-question students trend toward higher exam scores than report-writer clusters — related
• Cluster membership is significantly associated with grade level but not gender — related