Sentiment Analysis of Persian Political tweets using Machine Learning Techniques

Sentiment Analysis is a subfield of Natural Language Processing that has been extensively studied. Although Persian is the language of most modern information, the tools for processing it are limited. However, the ever-increasing impact of this task motivated this research to tackle it using Persian tweets. With the help of Iranian tweet datasets, we aim to predict polarity among tweets related to governance. We present the first study in this area of Persian tweets machine learning methods such as Decision Tree, Gradient Boosting, Random Forest and Support Vector Machines. With an accuracy of .۸۶, Random Forest had the best performance.

کلیدواژه ها:

Machine Learning ، Decision Tree ، SVM ، Random Forest ، Gradient Boosting.