An Information Extraction Method Based on Microblog Classification

Abstract

The invention relates to an information extraction method based on classification of microblogs. The method comprises the steps of (1) obtaining classification labels, (2) clearing up target labels, (3) carrying out label extraction by circulating a blog article according to the classification and the target labels and (4) carrying out filtration and disambiguation on extracted labels. The information extraction method based on classification of the microblogs is used for extracting secondary filtered labels in classified microblogs, all the labels can be found rapidly and comprehensively, filtration and screening are carried out, and accurate target labels are obtained.

Description

technical field

[0001] The invention belongs to a microblog information extraction method, in particular to an information extraction method based on microblog classification. Background technique

[0002] Micro-blog, or Micro-blog, is a broadcast-style social network platform based on Internet terminals sharing brief information through the attention mechanism, and has both social network and media features. With the continuous development of microblog technology, more and more users like to express their views on a certain event or a certain issue on microblog. In order to facilitate users to quickly and accurately find the microblogs they are interested in, it is necessary to extract the content information of blog posts and classify them in multiple dimensions. For example, it is possible to filter out microblogs related to food, but people with different tastes in different regions like different food. Therefore, further information extraction and multi-dimensional di...

Images