Open AccessBots Recognition in Social Networks Using the Random Forest Algorithm
Author(s) -
М. Г. Хачатрян,
П. Г. Ключарев
Publication year - 2019
Publication title -
mašinostroenie i kompʹûternye tehnologii
Language(s) - English
Resource type - Journals
ISSN - 2587-9278
DOI - 10.24108/0419.0001473
Subject(s) - computer science , python (programming language) , random forest , machine learning , artificial intelligence , algorithm , social network (sociolinguistics) , metric (unit) , software , world wide web , social media , operations management , economics , programming language , operating system
Online social networks are of essence, as a tool for communication, for millions of people in their real world. However, online social networks also serve an arena of information war. One tool for infowar is bots, which are thought of as software designed to simulate the real user’s behaviour in online social networks. The paper objective is to develop a model for recognition of bots in online social networks. To develop this model, a machine-learning algorithm “Random Forest” was used. Since implementation of machine-learning algorithms requires the maximum data amount, the Twitter online social network was used to solve the problem of bot recognition. This online social network is regularly used in many studies on the recognition of bots. For learning and testing the Random Forest algorithm, a Twitter account dataset was used, which involved above 3,000 users and over 6,000 bots. While learning and testing the Random Forest algorithm, the optimal hyper-parameters of the algorithm were determined at which the highest value of the F 1 metric was reached. As a programming language that allowed the above actions to be implemented, was chosen Python, which is frequently used in solving problems related to machine learning. To compare the developed model with the other authors’ models, testing was based on the two Twitter account datasets, which involved as many as half of bots and half of real users. As a result of testing on these datasets, F 1 -metrics of 0.973 and 0.923 were obtained. The obtained F 1 -metric values are quite high as compared with the papers of other authors. As a result, in this paper a model of high accuracy rates was obtained that can recognize bots in the Twitter online social network.