Predicting Online Education Dropout: A new Machine Learning Model based on Sentiment Analysis, Socio-demographic, and Behavioral Data
Bibliographic record
Abstract
Predicting student dropouts has always been crucial for traditional educational institutions, but it is even more so for distance learning platforms. A comprehensive approach incorporating diverse student data sources is necessary to make accurate predictions. In this paper, we introduce a new model utilizing a multi-modal fusion of sentiment analysis, performed on student comment data using the Bidirectional Encoder Representations from Transformers (BERT) model, with socio-demographic and behavioral data examined using the Extreme Gradient Boosting (XGBoost) model. Multi-modal data fusion improves the precision of student dropout prediction models, offering a deeper understanding of student dropout risks. Using the dataset obtained from the ChallengeU online platform, our model demonstrated remarkable success in identifying at-risk students, achieving an impressive 84% accuracy. Compared with the baseline model, this shows a noteworthy improvement, underlining the effectiveness of our method. What distinguishes our approach is using sentiment analysis alongside socio-demographic and behavioral data to predict school dropouts. For the first time, a dropout prediction model uses multi-modal data sources. The proposed approach could be vital in developing personalized strategies to reduce dropout rates and encourage perseverance.
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 | 0.001 | 0.002 |
| 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 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".