A method of filtering spam users in social network based on semi-supervised learning

Abstract

The invention discloses a method for filtering social network garbage users based on semi-supervised learning, and applies a collaborative training algorithm to the detection of social network garbage users. Most of the existing classifications of massive information in social networks use supervised learning algorithms, which are all classification models based on labeled data. There are not many ways to label user data. This paper proposes a method that uses collaborative training algorithms to apply multi-view and multi-classifiers to a large amount of unlabeled or a small amount of labeled social network data, so that classifiers on different views can learn from each other to achieve the purpose of data labeling.

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