Forecasting epidemic diseases with Arabic Twitter data and WHO reports using machine learning techniques

Twitter is one of the essential social media tools used by many people because they express their views, daily problems, and what suffer from health aspects. On Twitter, we can detect track spread most serious diseases like flu; analyzing people's tweets collecting reports organizations. In this paper, data was collected in Arabic language related to influenza using keywords. Then, applied several machine learning algorithms, which are random forest, multinomial naïve bayes, decision tree, voting classifier. We also found correlation between World Health Organization (WHO) website according three experiments. These experiments are: i) based on 13 countries regardless time, ii) Arab regions that depend these countries' dialects irrespective iii) all week number. The results show there a strong reports, means WHO together flu outbreaks world.