![]() | Only 14 pages are availabe for public view |
Abstract Microblogs and social media platforms are now considered among the most popular forms of online communication. Through a platform like twitter, much information reflecting people{u2019}s opinions and attitudes is published and shared among users on a daily basis. This has recently brought great opportunities to companies interested in tracking and monitoring the reputation of their brands and businesses, and to policy makers and politicians to support their assessment of public opinions about their policies or political issues. In recent years, sentiment analysis on twitter turned into a recognized shared task challenge. Researchers related to this topic focus only on the English texts with very limited resources interested in Arabic texts, especially for the Egyptian dialect. This thesis discusses a proposed approach for political sentiment analysis for Arabic slang and provides classifier model for the purpose of obtaining information from the tweets. The case study used Twitter data associated with the (2012) presidential election in Egypt. We collected (17290) tweets and annotated them into positive and negative. The thesis also provides a comparison of different machine learning techniques applied to the case of political sentiment analysis in social media. Several machine learning methods were used during experimentation session: Naive Bayes, multinomial naive bayes, support vector machines, K-nearest neighbor and decisions tree and combining different classification algorithms bagging, random forest and stacking |