Multi-label BERT classifiers slightly outperformed single-label Random Forest baselines on example-based F1 scores but under-performed with lower exact match ratios on MOOC cognitive presence classification¶
Claim · All claims
Evidence · 1 study · designr2·q3
Currency · newest study 2023 · not yet checked against its sources · 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.
q3 i? On the testing AgreementSet, multi-label deep learning classifiers achieved slightly higher example-based F1 scores and lower fully incorrect ratios than single-label Random Forest baselines, but lower exact match ratios. → Yuanyuan Hu 2023
Evidence¶
Yuanyuan Hu 2023¶
Yuanyuan Hu. (2023). Can Multi-Label Classifiers Help Identify Subjectivity? A Deep Learning Approach to Classifying Cognitive Presence in MOOCs. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-022-00310-5
q3 · i? · design · r2
Ten-fold cross-validated test on the AgreementSet of the LCT MOOC messages (Table 4), comparing multi-label BERT with and without data augmentation against Random Forest baselines with and without SMOTE. The article reports "the lower fully incorrect ratios but slightly higher example-based F1 scores" for the multi-label classifiers, while exact match ratios were lower.
"The multi-label classifiers achieved the lower fully incorrect ratios but slightly higher example-based F1 scores than the single-label baselines."
Discussion¶
Related Claims¶
- On the DisagreementSet, data augmentation improved the multi-label classifiers' exact match ratio and F1 score, while both ratios declined relative to the AgreementSet test — related
- Tested on coder-disagreement messages, multi-label classifiers labelled most messages into two adjacent phases with one predicted label matching the manual label, and partially correct predictions exceeded half of the set — related
- A support vector machine classifier outperformed decision tree and random forest models in predicting cognitive engagement levels of online discussion posts — related
- Academic word list count, word count, and Flesch-Kincaid grade level are the most important features for predicting cognitive engagement in discussion posts — related
- Multi-label classifiers predicted MOOC messages as one label or two adjacent cognitive presence phases only, while expert coders produced non-adjacent and three-phase labels on almost 4% of messages — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
multi-label-bert-f1-beats-rf-exact-match-lower |
title |
Multi-label BERT classifiers slightly outperformed single-label Random Forest baselines on example-based F1 scores but under-performed with lower exact match ratios on MOOC cognitive presence classification |
description |
Multi-label BERT classifiers slightly outperformed single-label Random Forest baselines on example-based F1 scores but under-performed with lower exact match ratios on MOOC cognitive presence classification |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2023 |
generated |
by process:wiki-ingest on 2026-10-27 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — yuanyuan-hu-2023 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.