Multimodal Educational Data Fusion for Students’ Mental Health Detection
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Mental health issues can lead to serious consequences like depression, self-mutilation, and worse, especially for university students who are not physically and mentally mature. Not all students with poor mental health are aware of their situation and actively seek help. Proactive detection of mental problems is a critical step in addressing this issue in this case. However, accurate detections are hard to achieve due to the inherent complexity and heterogeneity of unstructured multi-modal data generated by campus life. Against this background, we propose a detection framework for detecting students’ mental health, named CASTLE (educational data fusion for mental health detection). Three parts are involved in this framework. First, we utilize representation learning to fuse social life, academic performance, and physical appearance. An algorithm, named MOON (multi-view social network embedding), is proposed to combine students’ social life in a comprehensive way by fusing students’ heterogeneous social relations effectively. Second, a synthetic minority oversampling technique algorithm (SMOTE) is applied to the label imbalance issue. Finally, a DNN (deep neural network) model is utilized for the final detection. The extensive results demonstrate the promising performance of the proposed methods in comparison to an extensive range of state-of-the-art baselines.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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 it