Social media rumor detection method and system based on hierarchical heterogeneous graph neural network

A social media and neural network technology, applied in the field of social media rumor detection methods and systems, can solve the problems of inability to accurately describe rumor events, irregular expressions, event modeling, etc.

Pending Publication Date: 2021-10-19
FUZHOU UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing research mainly focuses on the three key elements of rumor content, publishing users, and dissemination modes, especially focusing on text content modeling, mining the expression of uncertainty as an important clue to identify rumors, but for social media , which has typical characteristics such as short text information and irregular expressions, making it difficult for the model to effectively model events
In addition, the existing research regards the above three key elements as independent event representation elements, ignoring the interrelationship, mutual complementation and mutual enhancement relationship among them, that is, separating the "user-event" and "user-event". Users” are closely related, which leads to the limited performance of the rumor detection model, so it cannot accurately describe the rumor event

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Social media rumor detection method and system based on hierarchical heterogeneous graph neural network
  • Social media rumor detection method and system based on hierarchical heterogeneous graph neural network
  • Social media rumor detection method and system based on hierarchical heterogeneous graph neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0047] Please refer to figure 1 , the present invention provides a social media rumor detection system based on layered heterogeneous graph neural network, comprising:

[0048] The data preprocessing module is used to preprocess text data, extract user static features, construct hierarchical heterogeneous graph structures, etc.;

[0049] An event encoding module, used to encode text containing information about propagation and diffusion structures;

[0050] User encoding module for learning user behavior characteristics;

[0051] A global heterogeneous graph encoding module to capture rich global structural information between events and users;

[0052] The rumor detection label output module is used to integrate text information, user behavior characteristics, and global heterogeneous graph information to complete the label prediction work of rumor ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a social media rumor detection method and system based on a hierarchical heterogeneous graph neural network, and the system comprises: a data preprocessing module which is used for preprocessing text data, extracting user static features, and constructing a hierarchical heterogeneous graph structure; an event encoding module which is used for encoding a text containing propagation and diffusion structure information; a user coding module which is used for learning user behavior features; a global heterogeneous graph coding module which is used for capturing rich global structure information between the event and the user; and a rumor detection label output module which is used for fusing the text information, the user behavior features and the global heterogeneous graph information to complete label prediction work of rumor detection. According to the method, local inline relationships between users and between texts can be effectively learned, user and text representations containing adjacent node information are generated, a global structure relationship between the user and an event is modeled and learned, and finally the authenticity of the event is identified.

Description

technical field [0001] The invention relates to the field of text detection, in particular to a social media rumor detection method and system based on a layered heterogeneous graph neural network. Background technique [0002] Rumor generally refers to a circulating statement or report whose authenticity has not been confirmed at the time of publication. This unverified statement may prove to be true, or may be partially or completely false, or its truth may not be verified for a long time. With the rapid development of social media platforms such as Twitter and Weibo, they have gradually replaced traditional media and become a convenient online platform for users to obtain information, express opinions and communicate with each other. Because social media has the essential characteristic of disseminating information at a high speed, while providing users with a quick way to obtain new information, it also provides a hotbed for the spread of rumors. Compared with traditio...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F16/35G06F16/36G06F40/216G06N3/04
CPCG06F16/353G06F16/374G06F40/216G06N3/047G06N3/045Y02D10/00
Inventor 廖祥文王灿杰林建洲林树凯陈泓敏
Owner FUZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products