The use of an artificial neural network to detect automatically managed accounts in social networks


Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription Access

Abstract

The problem of detection of automatically managed accounts (bots) in social networks has been considered. The method of their detection based on machine learning methods is proposed. The paper describes an example of a method based on artificial neural network learning. The parameters of a page in a social network used to detect bots have been presented. An experimental evaluation of the proposed system performance is given that demonstrates a high level of detection of bots in social networks.

About the authors

P. D. Zegzhda

St. Petersburg Polytechnic University

Author for correspondence.
Email: zeg@ibks.ftk.spbstu.ru
Russian Federation, St. Petersburg

E. V. Malyshev

St. Petersburg Polytechnic University

Email: zeg@ibks.ftk.spbstu.ru
Russian Federation, St. Petersburg

E. Yu. Pavlenko

St. Petersburg Polytechnic University

Email: zeg@ibks.ftk.spbstu.ru
Russian Federation, St. Petersburg

Supplementary files

Supplementary Files
Action
1. JATS XML

Copyright (c) 2017 Allerton Press, Inc.