BERT-CBA outperformed baseline tag recommendation methods on Precision@K, Recall@K, and F1@K under cross-validation¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2025 · checked against its sources 2026-10-28 (automated, 1 of 1 entry) · not reviewed by a person
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? BERT-CBA achieved higher Precision@K, Recall@K, and F1@K than MNB, SVM, BERT-FFNN, BERT-LSTM, and BERT-GRU in 5×2 cross-validation. → 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
Cross-validation comparison of six tag recommendation models on the Stack Overflow dataset. BERT-CBA "achieved higher Precision@K (Table 8), Recall@K (Table 9), and F1@K (Table 10) scores compared to the existing, baseline methods." Differences were tested with the 5×2 CV test using precision.
"The proposed method achieved higher Precision@K (Table 8), Recall@K (Table 9), and F1@K (Table 10) scores compared to the existing, baseline methods."
Discussion¶
Related Claims¶
- BERT-CBA outperformed BERT-FFNN by 6–15% on Precision@K, with t(5) = 6.56, p = .001, d = 4.64 — a narrower finding that bears on this claim
- BERT-CBA outperformed BERT-LSTM by 4–9% and BERT-GRU by 2–10% on F1@K — a narrower finding that bears on this claim
- BERT-CBA outperformed MNB by 40–73% across metrics, with t(5) = 5.55, p = .002, d = 10.20 for precision — a narrower finding that bears on this claim
- BERT-CBA outperformed SVM by 44–73% on Precision@K, with t(5) = 5.62, p = .002, d = 7.13 — a narrower finding that bears on this claim
- Fine-tuned BERT outperforms FFNN and LSTM deep learning architectures for classifying segments of written reflections, with weighted F1 average of .82 — related
- F1@K decreased as K increased for all methods — related
- The highway layer ablation showed no measurable performance difference between BERT-CBA variants — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
bert-cba-outperforms-baselines-cross-validation |
title |
BERT-CBA outperformed baseline tag recommendation methods on Precision@K, Recall@K, and F1@K under cross-validation |
description |
BERT-CBA outperformed baseline tag recommendation methods on Precision@K, Recall@K, and F1@K under cross-validation |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2025 |
source_checked |
2026-10-28 |
generated |
by process:wiki-ingest on 2026-10-28 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — olatinwo-2025 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.