| Abstrak/Abstract |
Freedom of social media users who are not controlled in giving opinions can make it easier for users to attack certain people, objects, or environments with hateful
language or commonly called hate speech. According to the Indonesia Criminal Investigation Police, 80% of cybercrimes reported were expressions of hatred. Preventive actions taken by Facebook & Twitter are deemed ineffective because checking hate speech is still manually through user reports. In this study, we used a machine learning algorithm, which is Support Vector Machine (SVM), to identify whether a speech is considered as hate speech or not. We combined the SVM with the Lexicon-based Features and Synonym-based Query Expansion method. The models were trained and evaluated by calculating Accuracy, Precision, Recall, and F-measure. This study shows that the use of the Synonym-based Query Expansion method can improve the performance of the SVM model with Lexicon-based as its feature. |
