MétaCan
Menu
Back to cohort
Record W4394729518 · doi:10.1145/3641181.3641186

Revisiting Annotations in Online Student Engagement

2024· article· en· W4394729518 on OpenAlexaff
Shehroz S. Khan, Sadaf Safa

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicOnline Learning and Analytics
Canadian institutionsUniversity of Toronto
FundersUniversitas Brawijaya
KeywordsComputer scienceStudent engagementWorld Wide WebMathematics educationPsychology

Abstract

fetched live from OpenAlex

Assessing the engagement of students in online classroom is crucial to meet their learning objectives. Many machine learning and deep learning models have been proposed to handle this problem using a variety of sensors, with videos cameras being the most prominent. However, most of these approaches are not interoperable because different datasets use different labeling protocols. As a result, the classification models range from binary, multi-class to regression problems. Another problem is the lack of rigor and definition of engagement to annotate the data. In this paper, firstly we showed inconsistencies in the labeling of a popular student engagement DAiSEE dataset. Then, we re-labeled more than 7000 videos of this dataset using a methodical engagement annotation protocol, HELP, to convert it from four class to binary classification problem. Further analysis highlights issues in DAiSEE annotation in comparison to the HELP protocol. Lastly, we tested three state-of-the-art deep learning and feature-based methods and discussed their performance. Data imbalance in the newly and previously annotated data was found to be the main issue in developing predictive models.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.031
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.010
Threshold uncertainty score0.024

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.031
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0030.003
Science and technology studies0.0010.001
Scholarly communication0.0030.004
Open science0.0010.004
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0030.003

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 head0.030
GPT teacher head0.365
Teacher spread0.334 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
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

Citations1
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicOnline Learning and AnalyticsFrench-language works237,207