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

A guessing method of microblog user's location

A user and microblogging technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem of not being able to overcome the sparsity of geographic vocabulary and the low accuracy of user location estimation

Active Publication Date: 2016-11-02
HANGZHOU DIANZI UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still two problems in this research: 1) The accuracy of user location estimation is not high; 2) The sparseness of geographical vocabulary cannot be well overcome

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
  • A guessing method of microblog user's location
  • A guessing method of microblog user's location
  • A guessing method of microblog user's location

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings, but are not limited thereto.

[0017] Such as figure 1 The shown geographical vocabulary learning process, its steps include:

[0018] First, collect user microblog corpus that has filled in specific location information;

[0019] Optionally, the microblog information of the portal microblog is collected through an open interface specified by the portal microblog. The project of collecting the user's location has filled in the microblog recently released by the user at the specific location as the location feature vocabulary learning microblog corpus. The recently released Weibo refers to the original Weibo text posted by the user and the comments made by the user when the user forwarded the Weibo, excluding the original Weibo reposted by the user; the collected Weibo corpus refers to each user who has filled in the specific location info...

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 user location estimation method which includes a location feature word learning process and a microblog user location estimation process. The location feature word learning process includes acquiring microblog corpus of users who have fill in information about locations, extracting nouns in the corpus, extracting location feature words on the basis of a feature extraction method and calculating the corresponding weight. The microblog user location estimation process includes acquiring location information of microblog users to be estimated and their fans as input, extracting to obtain a user microblog geography word set and a fan geography word set, calculating the weight corresponding to the user microblog geography word representative location and the weight corresponding to the fan geography word representative location, performing weighting summation on the weights of the location words, and outputting the location words with the maximum weight as estimated locations of the users. Microblog user location estimation can be more targeted, and locations of microblog users can be estimated more accurately by the microblog user location estimation method.

Description

technical field [0001] The invention belongs to the technical field of data mining in network microblogs, in particular to a method for estimating the positions of microblog users. Background technique [0002] There are currently many studies on location inference, including a large number of studies on location inference in blogs, web pages, and microblogging domains. The research results of these location predictions can provide location services for higher-level applications, such as event detection and news recommendation. These applications are all built on the assumption that the user's location information can be obtained. Unfortunately, location information in Weibo is sparse, and according to statistics, only 1% of Weibo uses geographic tags. It can be seen that the research on the location of Weibo users is very necessary. [0003] Hecht et al. (2011) proposed a multinomial Naive Bayesian model to infer user locations at the provincial level. Hecht et al. foun...

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 Patents(China)
IPC IPC(8): G06F17/30
Inventor 徐明王黠任一支张海平徐建郑宁
Owner HANGZHOU DIANZI UNIV
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