Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

LLM-BCgrading: Large language model-based Chinese medical long text classification for bladder cancer grade prediction.

Digital health·2025

Same author

Leveraging an Image-Enhanced Cross-Modal Fusion Network for Radiology Report Generation.

Journal of computational biology : a journal of computational molecular cell biology·2025

Same author

Multi-source biological knowledge-guided hypergraph spatiotemporal subnetwork embedding for protein complex identification.

Briefings in bioinformatics·2025

Same author

Heterogeneous graph contrastive learning with gradient balance for drug repositioning.

Briefings in bioinformatics·2024

Same author

MGRN: toward robust drug recommendation via multi-view gating retrieval network.

Bioinformatics (Oxford, England)·2024

Same author

Document-level biomedical relation extraction via hierarchical tree graph and relation segmentation module.

Bioinformatics (Oxford, England)·2024

Same journal

Pregnancy-Related Clinical Codes in Unlikely Populations in Primary Care.

JMIR medical informatics·2026

Same journal

Selecting, Scaling, and Measuring the Value of Ambient AI in a Nonacademic Health System: Multiphase Pilot Study.

JMIR medical informatics·2026

Same journal

Prediction of Early Hospital Admission (≤24 Hours) After Stroke Using Machine Learning and Deep Learning: Multicenter Study From China.

JMIR medical informatics·2026

Same journal

Assessing the Feasibility and Acceptability of Implementing a Preclinic Vital Signs Assessment in Primary Care: Cross-Sectional Pilot Study.

JMIR medical informatics·2026

Same journal

Candidate Passive Sensor Suite Technologies for Tactical Combat Casualty Care Environments: Comparative Assessment Study.

JMIR medical informatics·2026

Same journal

Relevance of the uMap Collaborative Platform as Support for Choropleth Mapping: A Traffic‒Light Statistical Signal Atlas of All-Cause Mortality-First French Lockdown.

JMIR medical informatics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 29, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Multifeature Fusion Attention Network for Suicide Risk Assessment Based on Social Media: Algorithm Development and

Jiacheng Li¹, Shaowu Zhang¹, Yijia Zhang¹

¹College of Computer Science and Technology, Dalian University of Technology, Dalian, China.

JMIR Medical Informatics

|July 13, 2021

Summary

This summary is machine-generated.

This study introduces an advanced model for suicide risk assessment using social media data. The new method effectively extracts key information for better detection of suicidal ideation.

Keywords:

attention mechanism infodemiology neural networks social media suicide risk assessment

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community

Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community

Published on: May 31, 2019

Related Experiment Videos

Last Updated: Oct 29, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community

Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community

Published on: May 31, 2019

Area of Science:

Computational linguistics
Clinical psychology
Artificial intelligence in healthcare

Background:

Suicide is a leading global cause of death.
Social media is a crucial data source for studying mental health conditions like depression and suicide.
Existing suicide risk assessment methods often fail to capture essential textual information.

Purpose of the Study:

To develop an efficient method for extracting core information from social media for suicide risk assessment.
To propose a multifeature fusion recurrent attention model for enhanced suicide risk assessment.

Main Methods:

Utilized bidirectional long short-term memory (BiLSTM) networks for text representation capturing context.
Implemented a self-attention mechanism to identify and extract critical information from social media posts.
Integrated linguistic features to augment the model's understanding and performance.

Main Results:

The proposed model demonstrated improved performance on the CLPsych 2019 shared task dataset.
Achieved performance gains in risk-F1 (3.3%), urgent-F1 (0.9%), and existence-F1 (3.7%).

Conclusions:

BiLSTM excels at long text representation, while attention mechanisms effectively pinpoint key information.
External linguistic features complement neural network extraction, enhancing overall model performance.
The developed model surpasses state-of-the-art methods, offering significant theoretical and practical value for suicide risk assessment.