Improve the automatic classification accuracy for Arabic tweets using ensemble methods

摘要

Tweets classification became interest topics in recent years, especially for the Arabic language. In this paper, the Arabic tweets are classified automatically into one of some predetermined categories mainly: sport, culture, politics, technology and general, based on their linguistic characteristics and their contents, also the classification accuracy is improved for Arabic tweets, by using ensemble methods mainly: bagging, boosting and stacking on the same dataset that we used it before in the classification, to verify of the results, and identify the best classifier gives high accuracy. The experimental results showed that using ensemble methods are better than using individual classifier, to improve the accuracy of classification. Increased accuracy of classifier Na?ve Bayes (NB) to 1.6%, classifier Sequential Minimal Optimization (SMO) to 2.2% and finally Decision Tree (J48) classifier reached up to 3.2%, comparing to using the J48, NB, or SMO as a single classifier.