Social network garbage user detection method integrated with multiple algorithms

Abstract

The invention discloses a social network garbage user detection method integrated with multiple algorithms, and the method comprises the steps: obtaining the user data from a social network in a mode of web crawler, and extracting the corresponding features through analyzing the behaviors of users to form a feature vector; carrying out the clustering of users in the social network through employing a clustering algorithm combining K-Means and DBSCAN; selecting the data nearby a cluster boundary and a data training support vector machine (SVM) classifier nearby a clustering center from the clustering result at the previous step, and obtaining a classifier model; and finally detecting the garbage users in the social networks through the SVM classifier model obtained through training. The method reduces the cost of manual marking of data, improves the detection accuracy, and is easy to implement.

Description

technical field [0001] The invention relates to the field of social network security, and relates to analyzing and processing spam users in social networks by using machine learning algorithms, and in particular to a method for detecting spam users in social networks that integrates multiple algorithms. Background technique [0002] Social Network (Social Network) is also known as Social Network Service (Social Network Service, SNS), Social Media Network (Social Media Networks, SMN) or Social Network Sites (Social Network Sites, SNS), which refers to those who share common interests, behaviors, backgrounds A network platform for people to build social relationships. With the rapid development of the Internet industry chain, certain changes have taken place in the Internet industrial structure and user behavior habits, and social networks are leading the new growth momentum of the Internet industry. The growth rate of users of mainstream foreign social networking platforms T...

AI Technical Summary

Problems solved by technology

[0008] (5) Maliciously adding friends, likes, voting, etc.

Detection using supervised learning algorithms requires the construction of labeled data to train classifiers, and the construction of labeled data often relies on expensive human inspection

However, spam users will bypass the current system detection by constantly adjusting and changing strategies, resulting in the invalidation of the constructed spam label library, thus causing spam user detection to fall into the problem of circularly constructing labeled training data and classifiers, which consumes a lot of labor cost and training cost

Although the use of unsupervised learning algorithms for detection does not require pre-labeled data to train classifiers, the accuracy of detection is relatively low

Images