MétaCan
Menu
Back to cohort
Record W4409078379 · doi:10.19173/irrodl.v26i1.8068

Automatic Classification of Online Learner Reviews Via Fine-Tuned BERTs

2025· article· en· W4409078379 on OpenAlexvenueno aff
Xieling Chen, Di Zou, Haoran Xie, Gary Cheng, Zongxi Li, Fu Lee Wang

Bibliographic record

VenueThe International Review of Research in Open and Distributed Learning · 2025
Typearticle
Languageen
FieldComputer Science
TopicOnline Learning and Analytics
Canadian institutionsnot available
FundersJilin Office of Philosophy and Social ScienceNational Natural Science Foundation of China
KeywordsComputer scienceEducational technologyDistance educationOnline learningMultimediaWorld Wide WebMathematics educationPsychology

Abstract

fetched live from OpenAlex

Massive open online courses (MOOCs) offer rich opportunities to comprehend learners’ learning experiences by examining their self-generated course evaluation content. This study investigated the effectiveness of fine-tuned BERT models for the automated classification of topics in online course reviews and explored the variations of these topics across different disciplines and course rating groups. Based on 364,660 course review sentences across 13 disciplines from Class Central, 10 topic categories were identified automatically by a BERT-BiLSTM-Attention model, highlighting the potential of fine-tuned BERTs in analysing large-scale MOOC reviews. Topic distribution analyses across disciplines showed that learners in technical fields were engaged with assessment-related issues. Significant differences in topic frequencies between high- and low-star rating courses indicated the critical role of course quality and instructor support in shaping learner satisfaction. This study also provided implications for improving learner satisfaction through interventions in course design and implementation to monitor learners’ evolving needs effectively.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.007
metaresearch head score (Gemma)0.005
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.905
Threshold uncertainty score0.570

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0070.005
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0020.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.093
GPT teacher head0.466
Teacher spread0.373 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designOther design
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations4
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueThe International Review of Research in Open and Distributed LearningSame topicOnline Learning and AnalyticsFrench-language works237,207