Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Microblog burst topic detection method based on burst word detection and filtering

A technology for topic detection and sudden words, applied in the Internet field, to achieve the effect of improving recall rate, improving accuracy and real-time performance

Active Publication Date: 2019-11-22
BEIJING UNIV OF POSTS & TELECOMM
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still some challenges for the sudden topic detection of Weibo.

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 burst topic detection method based on burst word detection and filtering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] In order to make the object, algorithmic calculation and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. The concrete realization of the algorithm of the present invention is divided into the following steps:

[0016] 1. Burst word detection based on word burst value calculation

[0017] Combining the basic weight and burst weight of words, a burst word algorithm based on burst value calculation is proposed. The algorithm mainly includes two parts: basic weight calculation and burst weight calculation. This process is illustrated by formula (1):

[0018] W(i,j)=λF(i,j)+(1-λ)B(i,j) (1)

[0019] where F(i,j) and B(i,j) represent word W respectively i The base weight and burst weight of the j-th time slice, W i Indicates the i-th word in the dictionary, and j indicates the sequence of time slices. λ is the adjustment coefficient (0<λ<1). The specific implementat...

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 provides a microblog emergency topic detection method based on emergency word detection and filtering. The method comprises three parts: burst word detection based on word burst value calculation, pseudo burst word identification based on burst value index average value calculation and burst topic identification based on topic keywords and burst word similarity. A theoretical systemis complete and innovative. The method is mainly used for social network text processing. A solution is provided for detecting microblog emergency topics and the method has very high practical value.

Description

technical field [0001] The invention belongs to the technical field of the Internet, and in particular relates to a sudden topic detection method. Background technique [0002] In recent years, with the rise of Web 2.0 social networks, microblog has become popular rapidly due to its advantages of convenience and quickness, and now it has developed into the main way of network information dissemination. Emergent topics spread very quickly in Weibo and can have a huge influence. Therefore, the social emergency topic detection technology on the Weibo platform is essential for the timely discovery of social hotspots, the rapid perception of public opinion on the Internet, and the early response to emergency topics. etc. have positive practical significance. However, there are still some challenges for burst topic detection on Weibo. First, the topics on Weibo are diverse. At the same time, various topics on Weibo, such as social topics, entertainment gossip topics, and person...

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): G06F17/27G06F16/33
CPCG06F16/3346G06F16/3334
Inventor 薛哲杜军平张强
Owner BEIJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com