A Hybrid Visual-ML Framework to Classify and Support Neurodiverse Learners Using Behavioural and Educational Data
Bibliographic record
Abstract
Early detection and focused interventions are essential for supporting neurodiverse adolescents, especially those with autism spectrum disorder (ASD). In order to classify and assist these learners, this work presents a hybrid visual machine learning (ML) system that combines behavioural and educational data. The proposed approach consists of five components: data preprocessing, orange model training, Tableau visual analytics, and deployment of the Streamlit online application. The dataset contains 704 occurrences and 20 variables that were taken from autism screening replies, such as demographics, medical history, and behavioural indicators. Three machine learning models: K-Nearest Neighbours (KNN), Random Forest, and Logistic Regression-were evaluated using 10-fold stratified cross-validation. Three machine learning models-K-Nearest Neighbours (KNN), Random Forest, and Logistic Regression-were evaluated using 10-fold stratified cross-validation. With an accuracy of 99.8% and an AUC of 1.000, Logistic Regression produced the best results. Random Forest and KNN both did well. The categorized results were shown in Tableau to enhance interpretability, and the trained model was made available as an easy-to-use web application using Streamlit. This eliminates the need for programming expertise and allows educators and stakeholders to enter new data, acquire visual insights, and receive predictions instantaneously. Unlike traditional methods, which often lack interpretability or utility, this framework provides a scalable, intelligible, and helpful solution. By combining interactive and visual tools with predictive accuracy, the solution connects machine learning with inclusive education methods and enhances decision-making for neurodiversity promotion.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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".