Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Mining Suicidal Ideation in Chinese Social Media: A Dual-Channel Deep Learning Model with Information Gain

Xiuyang Meng1,2, Xiaohui Cui1,2, Yue Zhang1,2

  • 1School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China.

Entropy (Basel, Switzerland)
|February 26, 2025
PubMed
Summary

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

The relationship between family socioeconomic status and cultural background on the career self-determination of Chinese and Kazakhstani students.

Frontiers in psychology·2026
Same author

Dual resistance to asparaginase and PD-1 blockade in extranodal natural killer/T-cell lymphoma: dismal outcomes from a multicenter cohort.

Haematologica·2026
Same author

Clinical significance of high-density lipoprotein cholesterol and its dynamic change in patients with lymphoma-associated hemophagocytic lymphohistiocytosis.

Therapeutic advances in medical oncology·2026
Same author

Comparative Analysis of Markerless Motion-Capture Models for Assessing Football Kinematics During 30 m Long-Pass Tasks.

Sensors (Basel, Switzerland)·2026
Same author

Neutrophil extracellular traps in thrombosis of hematologic malignancies: Underlying mechanisms and therapeutic opportunities (Review).

International journal of molecular medicine·2026
Same author

Heterogeneous and nonlinear associations between depressive symptoms and functional disability in older Chinese adults.

BMC psychology·2026

This study introduces DSI-BTCNN, a deep learning model for identifying suicidal ideation on Chinese social media. It enhances early detection and supports suicide prevention efforts.

Area of Science:

  • Artificial Intelligence
  • Computational Linguistics
  • Public Health

Background:

  • Suicidal ideation detection on social media is crucial for suicide prevention.
  • Unstructured social media data presents challenges for accurate identification.
  • Existing models may not fully capture linguistic nuances in Chinese text.

Purpose of the Study:

  • To develop a novel Chinese-based dual-channel deep learning model (DSI-BTCNN) for identifying suicidal ideation.
  • To enhance the model's ability to process text locality, context, and logical structure.
  • To improve the efficiency and robustness of suicidal ideation detection in real-time social media monitoring.

Main Methods:

  • A dual-channel deep learning architecture with multiple convolution kernels.
Keywords:
deep learning networksdual-channel modelentropy measurementinformation gainsocial media analysissuicide ideation detection

Related Experiment Videos

  • A fine-grained text enhancement approach for Chinese data.
  • An information gain-based IDFN fusion mechanism utilizing entropy assessment for feature allocation.

    • Main Results:

    • The DSI-BTCNN model achieved high performance: 89.64% accuracy, 92.84% precision, 89.24% F1-score, and 96.50% AUC.
    • Outperformed TextCNN and BiLSTM models by significant margins across key metrics.
    • Demonstrated a 17.53% increase in entropy value, indicating enhanced detection capability.

    Conclusions:

    • The DSI-BTCNN model offers a robust and effective solution for detecting suicidal ideation in Chinese social media data.
    • The fine-grained text enhancement and IDFN fusion mechanism contribute to improved feature mining and computational efficiency.
    • This model provides a promising tool for real-time monitoring and early intervention in suicide prevention initiatives.