Enhancing algorithmic assessment in education: Equi-fused-data-based SMOTE for balanced learning
Bibliographic record
Abstract
Recently, there has been a growing interest among researchers in enhancing the efficacy of learning through the utilization of diverse machine learning models within the field of artificial intelligence. However, imbalanced data distributions in educational datasets present a significant challenge to machine learning algorithms. This imbalance can result in biased models, untrustworthy outcomes, and poor performance. Data was gathered from a sample of 2176 first-year novice programming students in this study. Due to an alarming 76% failure rate, the imbalanced dataset was preprocessed before being oversampled with techniques such as SMOTE, SMOTE Borderline, SMOTE-ENN, and ADASYN. The proposed non-redundant synthetic data cooperation approach, named Equi-Fused-Data-based SMOTE, seeks to capitalize on the diversity of the obtained data by combining oversampled datasets. The balanced bagging model was then applied to the combined dataset to demonstrate the robustness of this approach. The promising results demonstrate the effectiveness of the Equi-Fused-Data-based SMOTE model, which achieved a higher Accuracy of 93.85%, a Precision, Recall and F1-score of 92,86%, and an AUC of 98.08%.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".