A comparative study of sentiment analysis using SVM and SentiWordNet

Sentiment analysis has grown rapidly and impacts on the number of services using the internet popping up in Indonesia. In this research, the sentiment analysis uses the rule-based method with the help of SentiWordNet and Support Vector Machine (SVM) algorithm with Term Frequency-Inverse Document Frequency (TF-IDF) as a feature extraction method. The data as the case study for the sentiment analysis is written in Indonesian language. Since the number of sentences in positive, negative and neutral classes is imbalanced, the oversampling method is implemented. For imbalanced dataset, the rule-based SentiWordNet and SVM algorithm achieve accuracies of 56% and 76%, respectively. However, for the balanced dataset, the rulebased SentiWordNet and SVM algorithm achieve accuracies of 52% and 89%, respectively.