Semi-supervised learning-based method for filtering junk users in social network

Abstract

The invention discloses a semi-supervised learning-based method for filtering junk users in a social network. A cooperative training algorithm is applied to the detection of the junk users in the social network. Massive information in the social network is classified mainly by utilizing a supervised learning algorithm at present; and the algorithm is based on a classification model built based on annotated data, but the social information scale is huge, the labor cost required for data annotation is high, and few methods for solving the problem of user data annotation of the social network exist. A method is proposed; and by referring to the cooperative training algorithm, multiple views and multiple classifiers are applied to a large amount of non-annotated social network data or a small amount of annotated social network data, so that the classifiers on different views learn mutually and the purpose of data annotation is achieved.

Description

technical field [0001] The invention relates to the field of social network security, in particular to a semi-supervised learning-based method for filtering social network junk users. Background technique [0002] The vigorous development of social networks (Social Networks, SN) has become a global social phenomenon. At present, the number of social networks is increasing rapidly, and the scale of users is constantly expanding. Among these Internet user groups, social networking has become an irreplaceable means of their daily communication. For example, the number of users of online social networking platforms such as Twitter, Facebook, and Sina Weibo has grown rapidly in recent years. While social networks bring convenience to people's lives, they also attract a large number of spam messages (Spam) and spammers (Spammer) because of their unique fission-style communication patterns. For example, spam information such as fake news, fake lottery winning information, and ille...

AI Technical Summary

Problems solved by technology

[0004] Most of the traditional spammer detection methods are classification models based on supervised learning. In order to improve the generalization ability of the classifier, a certain number of labeled samples must be added. However, the acquisition of such samples requires manual labeling. It is time-consuming and labor-intensive, and it is easy to form a labeling bottleneck problem

Images