الفهرس 
Chapter 1: introduction To Sentiment AnalysisOnly 14 pages are availabe for public view
 |  | from | 90 |  |  |
| | | from | 90 | | |
Abstract
Arabic sentiment analysis research existing currently is very limited. While sentiment analysis has many applications in English, the Arabic language is still recognizing its early steps in this field.
The proposed a system to enhance and optimize the accuracy of Arabic Sentiment Analysis (ASA) classifications based on machine learning techniques. In this aspect, nine supervised machine learning algorithms have been used for ASA. Namely, they are Logistic Regression (LR), Gradient Boosting (GB), Ridge Classifier (RC), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), K-Nearest Neighbor (KNN), Multi-layer Perceptron (MLP) and Naive Bayes (NB) classifiers.
A comparison of all nine classifiers is applied to a hotel reviews dataset prepared by using web scraping technique. We gathered 10000 hotel reviews from Booking.com website avoiding the neutral reviews. The final number of reviews was 7000 (3500 positive and 3500 negative) written in different forms of Arabic language.