Rumor early detection algorithm based on time sequence segmentation and fusion

An early detection and rumor technology, applied in computing, neural learning methods, natural language data processing, etc., can solve the problem of low early detection efficiency of the model, achieve the effect of curbing the spread of rumors in a short time and improving the detection effect

Active Publication Date: 2020-07-28
NANJING UNIV OF SCI & TECH
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide an early detection algorithm based on timing segmentation and fusion to solve the problem of low early detection efficiency of existing models

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 early detection algorithm based on time sequence segmentation and fusion
  • Rumor early detection algorithm based on time sequence segmentation and fusion
  • Rumor early detection algorithm based on time sequence segmentation and fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0036] This embodiment is carried out on a rumor data set, which contains a large number of rumor events, each rumor event has an original microblog and a label of authenticity, and a large number of tweets or comments related to the topic constitute a rumor event. The rumor event can be marked as E, where the earliest tweet can be regarded as the original Weibo published at time 0 c 0 , other tweets c i Then there is a corresponding release time t i , i>0. The representation of rumor events can be further extended as E={(c 0 ,0), (c 1 , t 1 ),..., (c m , t m )}, where m represents the number of tweets. Rumor event E also has a corresponding label Y to mark whether it is true or false.

[0037] Such as figure 1 As shown, the early detection algorithm for rumors based on timing segmentation and fusion includes the following steps:

[0038] Step 1. Rumor dissemination is a process of rapid increase in the early stage and slow decrease in the later stage. The timeline ...

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 discloses a rumor early detection algorithm based on time sequence segmentation and fusion. The rumor early detection algorithm comprises the following steps: segmenting a microblog rumor propagation timeline into a plurality of time windows according to a development rule; preprocessing the microblog or comment text in each time window; independently training an encoder for the datain each time window; splicing the code obtained by each time window with the code of the previous time window along a time line to form an incremental training network; and carrying out independent classification under each time window, so that authenticity detection can be conveniently carried out on rumor events at different time points. According to the method, the rumor detection task is converted from an integrated text classification task into a time sequence-based incremental classification task, and the problem of low rumor early detection precision is effectively solved.

Description

technical field [0001] The invention relates to the technical field of natural language processing applications, in particular to an early detection algorithm for rumors based on timing segmentation and fusion. Background technique [0002] Today, a large number of active users on social networking platforms provide favorable conditions for the online spread of rumors. A rumor is defined as a story or a statement whose truth is unsubstantiated rather than necessarily false. The spreading of false rumors may mislead the public, disrupt normal social order or endanger personal life. In the face of massive Weibo rumors, in order to detect rumors as early as possible and curb their spread, researchers began to use automatic rumor detection methods to replace time-consuming manual detection. [0003] Rumor detection is to analyze the authenticity of each Weibo event on the rumor data. At present, most works use the data of all moments on the timeline of each Weibo event as a 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): G06F16/35G06F16/33G06F40/284G06N3/04G06N3/08
CPCG06F16/35G06F16/334G06N3/084G06N3/045
Inventor 夏睿宣凯洲
Owner NANJING UNIV OF SCI & TECH
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