Modelling Of The Fake Posting Recognition In On-Line Media Using Machine Learning

Discuss content in the online web space has a significant impact on social life in recent years, especially in the political world. The impact of social networks has its advantages and disadvantages. An important disadvantage is a rising of the antisocial content in online communities. The antisocial content represents a serious and actual problem that is reinforced by a simplifying the process of creating and disseminating of antisocial posts. A typical example is a spreading of fake reviews. Detection of fake reviews is becoming one of the most important areas of research in last years. It is easier to track the impact of fake reviews than to detect them. The aim of this paper is to create suitable models for the fake reviews recognition using machine learning algorithms particularly decision tree, random forests, support vector machine and naive Bayes classifier. Using a confusion matrix, several indicators of binary classification efficiency were quantified in the process of these models testing.