Microblog rumor detection method and system based on user relationship structure feature

A technology of structural features and detection methods, applied in the fields of intelligent text analysis, artificial intelligence, and public opinion analysis, can solve the problems of ignoring user characteristics and integrating user characteristics, and achieve the effect of improving F1 value, improving accuracy and improving accuracy.

Inactive Publication Date: 2019-10-22
INST OF INFORMATION ENG CAS
View PDF9 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method ignores the role of user characteristics an

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
  • Microblog rumor detection method and system based on user relationship structure feature
  • Microblog rumor detection method and system based on user relationship structure feature
  • Microblog rumor detection method and system based on user relationship structure feature

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below through specific embodiments and accompanying drawings.

[0041] The invention uses a graph convolutional neural network to model the user relationship structure, characterizes the user model, and proposes a rumor detection method and system based on user relationship structure characteristics. The following is an introduction to the user relationship structure model, rumor detection method and system.

[0042] 1. User relationship structure model

[0043] Microblog data flow can be regarded as a set S=(T,U) including topic set T and user set U, where T=(T 1 , T 2 , T 3 …T i …T n ), C i Indicates the same as the source tweet r i All tweets in chronological order related to t i (i=1~m) set, ie T i =(r i ,t 1 , t 2 ,...,t m ). U=(U 1 ,U 2 ,U 3 … U i … U n ), U i means T i The collecti...

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 microblog rumor detection method and system based on user relationship structure features. The method comprises the following steps: 1) constructing a user relationship structure chart according to user behavior information, and modeling the user relationship structure chart to obtain a user vector; 2) constructing a propagation tree according to a propagation path of the microblog topic stream data, and encoding the propagation tree to obtain a propagation tree vector; and 3) cascading the user vector and the propagation tree vector, and inputting the user vector and the propagation tree vector into a neural network to judge whether the microblog topic is a rumor. The system includes a user encoder, a propagation tree encoder, and an integrator. According to themethod, users participating in the rumor propagation process are modeled to obtain vector representations of all the users in the microblog data stream, and useful detection factors are added in therumor detection process, so that the effect of user characteristics is reflected, and the accuracy and F1 value of a rumor detection system are improved.

Description

technical field [0001] The invention belongs to the technical fields of artificial intelligence, intelligent text analysis, and public opinion analysis, and relates to a rumor detection method, in particular to a microblog rumor detection method and system based on user relationship structural features. Background technique [0002] Weibo rumors refer to fabricated statements without factual basis that are spread through social media networks (such as Sina Weibo, Tencent Weibo, Twitter, etc.). Weibo rumors involve social, political, economic, cultural and other content, such as social emergencies, political elections, hot events, etc. The spread of Weibo rumors has the characteristics of suddenness, rapid spread and wide range of influence, so it is very easy to cause great harm to the country and society. For example, someone is fleshed out because of his similar appearance to the suspect in a certain case, which brings great trouble to his work and life and damages his pe...

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): G06F17/27G06N3/04G06F16/951
CPCG06F16/951G06F40/279G06N3/045
Inventor 黄琪周川胡玥谭建龙郭莉
Owner INST OF INFORMATION ENG CAS
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap