Development of Classification Model based on Arabic Textual Analysis to Detect Fake News: Case Studies

Abstract

The ease of communication that has been made possible by chat messaging platforms, such as WhatsApp and Line, and their increased use and ubiquity in society, have motivated purveyors of fake news to create and present their news as legitimate. Though different organisations continued their efforts to resolve this problem, many of the developed solutions rely on verifying the associated metadata, which are not always available. Several studies have attempted to identify fake news by analysing textual content; however, there is a lack of studies on Arabic language sources. Our work filled this gap; we proposed a machine learning model that classifies Arabic fake news based on textual analysis. This paper shows the feasibility of our approach to classify Arabic text in social media applications.