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.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Number of social network users worldwide from 2010 to 2019. http://www.statista.com/statistics/278414/number-of-worldwide-social-network-users/.
The first lessons of Tunisian cyber-revolution. http://www.golos-ameriki.ru/a/cyberrevolution-tauinis-2011-01-17-113877164/192340.html.
Khaikin, S., Neironnye seti: Polnyi kurs (Neural Networks: Full Course), Moscow: Vil’yams, 2006, 2nd ed.
The principle of learning a multilayer neural network using the back propagation algorithm. http://robocraft. ru/blog/algorithm/560.html.
PyBrain’s documentation. http://pybrain.org/docs/.
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © P.D. Zegzhda, E.V. Malyshev, E.Yu. Pavlenko, 2017, published in Problemy Informatsionnoi Bezopasnosti, Komp’yuternye Sistemy.
About this article
Cite this article
Zegzhda, P.D., Malyshev, E.V. & Pavlenko, E.Y. The use of an artificial neural network to detect automatically managed accounts in social networks. Aut. Control Comp. Sci. 51, 874–880 (2017). https://doi.org/10.3103/S0146411617080296
Received:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411617080296