Depression Micro-Expression Recognition Technology Based on Multimodal Knowledge Graphs
Bibliographic record
Abstract
According to authoritative surveys, 24.6% of contemporary college students experience varying degrees of mental health issues, with an annual increase of 1-3%.Severe depression, in particular, can lead to campus crises.Research by experts has demonstrated that microexpression recognition plays a significant predictive role in depression and holds considerable clinical value.This study first collects multimodal data from conversations between students and psychological counselors using professional equipment, including speech, video, and psychological scale data, to construct a multimodal psychological dataset for college students.The study utilizes a Kinect camera to convert speech into text for analysis and performs micro-expression analysis on video images.Addressing the limitations of traditional expression recognition methods in capturing subtle microexpressions, this paper proposes a micro-expression recognition model based on a Convolutional Neural Network (CNN)+ Graph Convolutional Network (GCN) transfer learning network.Leveraging the unique advantage of GCNs in automatically updating node information, the model captures the dependencies between image data and corresponding emotional labels in micro-expression sequences.The network model is pre-trained on the CAS(ME) 3 dataset to obtain initial parameters, followed by transfer learning to retrain the model for application to the college students' multimodal psychological dataset, ultimately producing representation vectors of micro-expressions.By correlating these representation vectors with various emotional categories, a multimodal knowledge graph based on video, speech, and psychological scale data is constructed.Experimental comparisons demonstrate that the proposed model effectively enhances micro-expression recognition performance and accurately identifies students' depressive states when combined with the multimodal knowledge graph.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".