HEDL: Deep learning multiple approaches for early detection of depression using sarcastic text
Bibliographic record
Abstract
Sarcasm is particularly notorious towards mental health, and thus it is quite essential for early identification of depressive indicators. This paper introduces the Hybrid Ensemble Deep Learning model as novel for the task of the detection of sarcasm task, targeting the weaknesses which were found in traditional approaches of SVC, DT, RF, and LR by using unique combinations of CNN, LSTM, and GRU to capture the sarcasm patterns that appear fine feature representation and enhanced robustness and accuracy. Our model uniquely integrates the architectures of CNN, LSTM, and GRU into one framework for capturing more complex patterns in feature representation, accuracy, and robustness. We tested it on a news headline dataset; HEDL gained 84 % accuracy along with marked reduction in false positives compared to baseline models, which improved the accuracy as well as the recall. Results of the experiment do support that the HEDL model is indeed much more accurate and reliable sarcastic detection methodology; it can have applications such as monitoring mental health or analysing sentiment.•Proposed the Hybrid Ensemble Deep Learning Algorithm (HEDL) for text data.•The proposed model outperforms traditional models in cognitive skill impairment detection.•Demonstrated scalability for diverse healthcare datasets.
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 | 0.001 |
| 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".