Topic discovery method of social media big data based on knowledge graph

Abstract

The invention relates to a social media large data subject discovering method based on a knowledge map. The social media large data subject discovering is realized by four steps of knowledge map probability processing, social media large data semantic similarity calculating, subject fuzzy density clustering and weak information subject filtering. The knowledge map probability processing step is to complete confidence assessment and true probability value generation of a triad fact in the knowledge map. The social media large data semantic similarity calculating step is to achieve semantic mapping structure of each pair of documents and semantic similarity assessment among the documents based on an approximate map matching strategy. The subject fuzzy density clustering step is to obtain different subjects of the social media large data and automatically determine the number of the subjects. The weak information subject filtering step is to delete the subjects with less semantic strength and return an optimal subject list to a user. Compared with the prior art, the method has the advantages of being high in extendibility degree, strong in self-adapting capability, high in accuracy and the like, and being effectively used in the fields of social public safety, public health care, Internet depth information service, e-commerce and the like.

Description

technical field [0001] The present invention relates to a topic discovery method, in particular to a knowledge map-based social media big data topic discovery method. Background technique [0002] In recent years, with the rapid development of technologies such as cloud computing, mobile communications, and social networks, the big data contained in social media platforms, that is, social media big data, has become more and more manifested in the 4 "V" (Volume, Velocity, Variety, Veracity) characteristic. With the accumulation of time, social media big data contains a wealth of social information, including network mapping of a large number of important social event clue information, and these network mapping information usually seem to be disorganized. In-depth analysis and mining of social media big data, quickly and accurately discover the hidden deep-seated themes, and then effectively predict the future development trend of social events on the basis of the existing di...

AI Technical Summary

Problems solved by technology

Due to the short content and high degree of fragmentation of social media big data, these methods have obvious defects in capturing data semantic information, automatically determining the number of topics, and filtering weak information topics, which seriously affects the quality of discovered topics.

Images