Unlock instant, AI-driven research and patent intelligence for your innovation.

Rumor propagation tree structure optimization method based on site consistency

An optimization method and propagation tree technology, applied in the field of authenticity of social media information release, can solve problems such as message dissemination structure optimization, and achieve the effect of reducing computational time complexity, improving performance, and optimizing performance

Active Publication Date: 2020-08-25
HARBIN ENG UNIV
View PDF11 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing research on rumor detection based on the structural characteristics of rumor propagation has not considered the problem of optimizing the structure of news propagation.

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
  • Rumor propagation tree structure optimization method based on site consistency
  • Rumor propagation tree structure optimization method based on site consistency
  • Rumor propagation tree structure optimization method based on site consistency

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be further described below in conjunction with the accompanying drawings.

[0024] by figure 1 As an example, the propagation tree optimization problems based on breadth-first and depth-first based on consistent standpoints are introduced successively. figure 1 The structure tree diagram of rumor propagation in some original social media, figure 2 and image 3 The tree diagrams of the social media rumor propagation structure after applying the propagation tree optimization methods based on breadth-first and depth-first respectively. In the present invention, it is intended to propose a propagation tree optimization algorithm based on consistent standpoints applied to social media rumor detection scenarios, including a breadth-first-based propagation tree optimization method and a depth-first-based propagation tree optimization method, which can greatly reduce Propagate the number of branches and nodes in the tree, thereby reducing the comp...

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 belongs to the technical field of authenticity of social media information release, and particularly relates to a rumor propagation tree structure optimization method based on site consistency. For a top-down recurrent neural network model rumor detection scene based on a tree structure in social media, nodes with a same standing field in a rumor propagation tree structure can be merged into a super node. Standing field representation of the node to father nodes of the node is enhanced, the propagation tree structure is optimized, and rumor detection performance is improved. Thenumber of branches and the number of nodes in the propagation tree can be greatly reduced, so that the calculation time complexity of rumor detection is reduced, and the rumor detection performance isoptimized.

Description

technical field [0001] The invention belongs to the technical field of authenticity of social media information release, and in particular relates to a rumor propagation tree structure optimization method based on consistent positions. Background technique [0002] Rumors are generally defined as information that arises and spreads among people of unproven truth value or is deliberately false. The spread of rumors has been further facilitated in recent years as the popularity of social media on Twitter, Facebook, etc. has enabled unreliable sources to spread a lot of unverified information among people. Therefore, it becomes even more important to track and debunk rumors in real time. However, traditional feature-based methods extract features from the statistical information of fake news, the author of the message and their responses, and form a flat feature vector for rumor detection. However, this method ignores the propagation structure of the message, which leads to t...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/9536G06K9/62G06N3/04G06Q50/00
CPCG06F16/9536G06Q50/01G06N3/045G06F18/24323
Inventor 王巍杨武苘大鹏玄世昌吕继光刘雷
Owner HARBIN ENG UNIV