Detecting Fake Users on Social Media with a Graph Database

Abstract

Social media has become a major part of people’s daily lives as it provides users with the convenience to connect with people, interact with friends, share personal content with others, and gather information. However, it also creates opportunities for fake users. Fake users on social media may be perceived as popular and influential if not detected. They might spread false information or fake news by making it look real, manipulating real users into making certain decisions. In computer science, a social network can be treated as a graph, which is a data structure consisting of nodes being the social media users, and edges being the connections between users. Graph data can be stored in a graph database for efficient data analysis. In this paper, we propose using a graph database to achieve an increased scalability to accommodate larger graphs. Centrality measures as features were extracted for the random forest classifier to successfully detect fake users with high precision, recall, and accuracy. We have achieved promising results especially when compared with previous studies. 

Using graph solutions to identify "troll farms" and fake news propagation channels

“…Classifier tests in the case of the follower network essentially confirmed the conclusions regarding the effective operation of the random forest from previous studies [10] [11]. It turned out, however, that the KNN classifier on the same set of MIB followers achieved better results than the random forest used in previous studies.…”

“…The obtained values are slightly worse than those obtained in the research from 2021 [11] on the exclusive MIB set. However, the MIB set allowed us to build a classifier and significantly lower ability to generalize in detecting fake users, in contrast to the set of FakeNewsFollowers obtained in this work.…”

“…The extracted features for this set allowed us to obtain results similar to the work [11] where closeness centrality was introduced. At the same time, it can be seen that betweenness centrality, in this case, does not play a significant role in classifying "fake" users.…”

“…It creates a significant advantage because we can already take action, then -observe the user and start analyzing their content with other solutions to detect false information. References [10] and [11] examined follower networks and followed accounts using graph centrality measures. In addition, it was possible to classify online trolls from the 2016 US presidential campaign by creating a network of users who retweeted their posts [12].…”

“…These classifiers were subjected to a stratified 10-fold cross-validation study following a review of popular methods for testing the efficiency of classifiers [20]. Stratification is a good solution for unbalanced sets, and the K-fold method itself has already been used in previous works on this topic [10] [11]. It is also widely used, and effective [21].…”