A disinformation-driven method for finding subject matter experts in social networks

Abstract

The invention discloses a search method for social network subject matter experts driven by false information, including: using social network data sets to construct candidate user documents, using candidate user documents and false information to be queried to construct a probability graph model; using candidate The user documents and the false information to be queried are used to train the probabilistic graphical model. When the parameters of the probabilistic graphical model converge, the candidate user vector and the false information vector to be queried are obtained; by calculating the candidate user vector and the false information vector to be queried Cosine distance, to obtain the similarity between the candidate user and the false information to be queried, and use the similarity to obtain the query result. The present invention can well deal with social network situations, deal with false information containing multiple topics, and take into account the connections between users in the social network.

Description

technical field [0001] The invention belongs to the field of information retrieval, and more specifically relates to a search method for a social network subject matter expert driven by false information. Background technique [0002] With the continuous development of Internet technology, especially Web2.0 technology and wireless communication technology, the number of Internet users in my country has grown rapidly. According to the 39th "China Internet Development Status" statistical report released by China Internet Network Information Center (CNNIC), As of December 2016, China's Internet penetration rate reached 53.2%, and the number of Internet users reached 731 million, which is equivalent to the total population of Europe. Massive Internet users have promoted the vigorous development of various social applications, such as microblogging social networks (Twitter, Sina Weibo, etc.). As of August 2016, Sina Weibo had 282 million monthly active users, maintaining a growth...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above defects or improvement needs of the prior art, the present invention provides a search method for social network subject matter experts driven by false information, thereby solving the problem that the prior art cannot cope well with social network situations, let alone dealing with multiple misinformation on the subject, ignoring the technical problems of the connections that exist between users in the social network

Images