Anomaly Detection Method for Online Discussion

Abstract The presented article deals with the analysis of users discussing online, on the two most famous Slovak servers Cas.sk and Sme.sk. They provide a sufficiently representative sample of data to detect and compare the essential common behavioral characteristics of users in online discussions. This also makes it possible to identify user partitioning and to develop new methods to detect anomalies, specifically designed to differentiate discussing users with abnormal behavior. In the presented article, such a method is defined, with multiple tuning parameters, using a classification neural network. The proposed method is applied on real data, obtaining encouraging results.