Suspicious group discovery method and device

Abstract

The invention provides a suspicious group discovery method and device. The method comprises the steps of firstly obtaining a user and text contents published by the user; calculating the similarity between a large number of texts by utilizing a specific algorithm; by taking the similarity between the texts published by the user as a connection relation, establishing a similar user network; and finally discovering a suspicious group by community division of the user similar network. The similar text-based suspicious group discovery is realized.

Description

technical field [0001] This specification relates to the Internet field, and in particular to a suspicious group discovery method and device. Background technique [0002] The increasing development of the Internet community platform provides a convenient and effective communication platform for the majority of users, but also produces a large number of illegal and prohibited content. Usually, gray and black production personnel will use gangs to commit crimes to ensure that their illegal content is widely recognized. spread. [0003] In the existing technology, in order to maintain the healthy development of the community, the community platform often uses the direct relationship network between members to mine groups, for example, based on a certain black user, using each other as friends, following the same blogger, and being in a certain group Group and other information to expand the relationship, and then dig out related gangs. [0004] However, with the escalation o...

AI Technical Summary

Problems solved by technology

[0004] However, with the escalation of the confrontation between the platform and the dark industry, in order to avoid the monitoring, detection, and punishment of the community platform, the dark industry is also consciously downplaying the relationship between its members, and using various methods to control its own behavior. Covering up, for example, members of the same group who spread a large amount of illegal information such as advertisements and pornography are not directly connected to the community platform, but they will spread a large amount of similar advertising information, and increase the difficulty of platform risk prevention and control by modifying some of the text

From a macro point of view, they may be individual individuals. At this time, the relationship-based gang mining method cannot achieve a good mining effect

Images