Sentiment analysis (analisis sentimen) in Bahasa Indonesia using Python.
- Python 2.7.X
- nltk 3.2.4
- scikit-learn 0.19.0
The purpose of sentianalysis-id is to classify a sentence whether it is positive, negative or neutral. Sentianalysis-id uses classifier to predict the sentiment of sentences. Classifier is trained using labeled datasets that are modeled first using the feature vector. The feature vector is used to build the model data training learned by the classifier, then the classifier can be used to classify invisible sentences.
We use three methods, which are Naive Bayes, Max Entropy and SVM to compare the result.