BERT-CBA outperformed MNB by 40–73% across metrics, with t(5) = 5.55, p = .002, d = 10.20 for precision¶

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? BERT-CBA outperformed MNB by 40% to 70% on Precision@K, 41% to 73% on Recall@K, and 40% to 73% on F1@K. → Olatinwo 2025

Evidence¶

Olatinwo 2025¶

Olatinwo, S. O., & Demmans Epp, C. (2025). Predicting Tags for Learner Questions on Stack Overflow. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-024-00441-x

q2 · i? · design · r2

5×2 cross-validation comparison against the multinomial naive Bayes baseline. The article reports "t(5) = 5.55, p = .002, d = 10.20" for precision and percentage ranges for recall and F1.

"BERT-CBA outperformed MNB by 40% to 70% on Precision@K for all values of K: t(5) = 5.55, p = .002, d = 10.20. BERT-CBA also outperformed MNB by 41% to 73% in Recall@K (Table 9), and the F1@K values were 40% to 73% higher (Table 10)."

Discussion¶

Related Claims¶

• BERT-CBA outperformed BERT-FFNN by 6–15% on Precision@K, with t(5) = 6.56, p = .001, d = 4.64 — related
• BERT-CBA outperformed SVM by 44–73% on Precision@K, with t(5) = 5.62, p = .002, d = 7.13 — related
• BERT-CBA outperformed baseline tag recommendation methods on Precision@K, Recall@K, and F1@K under cross-validation — a broader claim this one bears on
• BERT-CBA outperformed BERT-LSTM by 4–9% and BERT-GRU by 2–10% on F1@K — related
• The highway layer ablation showed no measurable performance difference between BERT-CBA variants — related