Twitter Sentiment Analysis for Reviewing Tourist Destinations in Saudi Arabia using Apache Spark and Machine Learning Algorithms

The appearance of big data has created new challenges for data analysis teams especially dealing with unstructured data in text form. Many applications increasingly include a large amount of this type of data. Example of such data is data collected from Twitter. Adequate use of Machine Learning (ML), big data tools and social media platforms can solve several problems. The aim of this research is to apply sentiment analysis using Arabic tweets of tourism in Saudi Arabia and determine the most visited places.  Ara Senti corpus was used as the labelled data to perform machine learning for sentiment analysis to deal with the Arabic morphology.  The three-classes classification (Positive, Negative, or Neutral) was performed using Decision Tree, Random Forest, Logistic Regression and Naïve Bayes. The results showed that the highest performance achieved was 86% using Logistic Regression with Term Frequency–Inverse Document Frequency (TF-IDF) representation and Naïve Bayes with Bag-of-Words model compared with both random forest and decision tree.  The trainable classifier was applied to predict classes on collected data from Twitter for reviewing Kingdom of Saudi Arabia (KSA) destinations to finally present a rating of the most visited places on KSA. There are five most visited places in Saudi Arabia (Riyadh, Alula, Hail, Taif and Tabuk).