Deep Hierarchical Attention Active Learning for Mental Disorder Unlabeled Data in AIoMT
Bibliographic record
Abstract
In the Artificial Intelligence of Medical Things (AIoMT), Internet-Delivered Psychological Treatment (IDPT) effectively improves the quality of mental health treatments. With the advent of COVID-19, psychological tasks have become overloaded and complicated for medical professionals due to the overlap of sentimental values. The development of an AIoMT tool requires labeling of data to achieve clinical-level performance. Text data requires an appropriate set of linguistic features for vector latent representation and segmentation. Emotional biases could lead to incorrect segmentation of patient-authorized texts, and labeling emotional data is time-consuming. In this article, we propose an assistant tool for psychologists to assist them in mental health treatment and note-taking. We first extend the word and emotion lexicon and then apply a hierarchical attention method to support data labeling. The learned latent representation uses word position prediction and sentence-level attention to create a semantic framework. The augmented vector representation helps in highlighting words and classifying nine different symptoms from the text written by the patient. Our experimental results show that the emotion lexicon helps to increase the accuracy by 5% without affecting the overall results, and that the hierarchical attention method achieves an F1 score of 0.89.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".