Related Experiment Video
Updated: Jan 19, 2026
03:31
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
1.0K
Self Multi-Head Attention-based Convolutional Neural Networks for fake news detection.
Yong Fang1, Jian Gao1, Cheng Huang1
1College of Cybersecurity Sichuan University, Chengdu, Sichuan, China.
Plos One
|September 27, 2019
Summary
This study introduces a new model for detecting fake news using content analysis. The Self Multi-Head Attention-based Convolutional Neural Networks (SMHA-CNN) model achieves high accuracy in identifying misinformation, crucial for combating its societal impact.
Area of Science:
- Computer Science
- Artificial Intelligence
- Information Science
Background:
- Social media's growth has increased exposure to fake news.
- Fake news negatively impacts individuals and society.
- Accurate fake news detection is a significant research challenge.
Purpose of the Study:
- To develop a highly accurate model for detecting fake news.
- To evaluate the model's performance using content analysis.
Main Methods:
- Developed the Self Multi-Head Attention-based Convolutional Neural Networks (SMHA-CNN) model.
- Utilized convolutional neural networks and a self multi-head attention mechanism.
- Conducted experiments on a public dataset with 5-fold cross-validation.
Main Results:
- Achieved a precision rate of 95.5%.
- Achieved a recall rate of 95.6%.
- Demonstrated the model's effectiveness in fake news detection.
Conclusions:
- The SMHA-CNN model accurately detects fake news based on content.
- The proposed model offers a promising solution for combating misinformation online.
