Multifeature Fusion Attention Network for Suicide Risk Assessment Based on Social Media: Algorithm Development and Validation
Bibliographic record
Abstract
BACKGROUND: Suicide has become the fifth leading cause of death worldwide. With development of the internet, social media has become an imperative source for studying psychological illnesses such as depression and suicide. Many methods have been proposed for suicide risk assessment. However, most of the existing methods cannot grasp the key information of the text. To solve this problem, we propose an efficient method to extract the core information from social media posts for suicide risk assessment. OBJECTIVE: We developed a multifeature fusion recurrent attention model for suicide risk assessment. METHODS: We used the bidirectional long short-term memory network to create the text representation with context information from social media posts. We further introduced a self-attention mechanism to extract the core information. We then fused linguistic features to improve our model. RESULTS: We evaluated our model on the dataset delivered by the Computational Linguistics and Clinical Psychology 2019 shared task. The experimental results showed that our model improves the risk-F1, urgent-F1, and existence-F1 by 3.3%, 0.9%, and 3.7%, respectively. CONCLUSIONS: We found that bidirectional long short-term memory performs well for long text representation, and the attention mechanism can identify the key information in the text. The external features can complete the semantic information lost by the neural network during feature extraction and further improve the performance of the model. The experimental results showed that our model performs better than the state-of-the-art method. Our work has theoretical and practical value for suicidal risk assessment.
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 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 | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".