ANALISIS SENTIMEN TWITTER UNTUK TEKS BERBAHASA INDONESIA DENGAN MAXIMUM ENTROPY DAN SUPPORT VECTOR MACHINE

Sentiment analysis in this research classified textual documents into two classes, positive and negative sentiments. The data were obtained from query of tweets in Twitter, a social networking site. This research studied Indonesian tweets. The study aimedtodetermine public sentiment toward particular object presented inTwitter using Indonesian for the market research on the public opinion. The data collected were prepocessed and POStagger to generate classification models through the training process. The method of collecting sentimental words was committed by using approach of dictionary created in the study. The dictionary consisted of 18.069 words. Maximum Entropy algorithm is used for POStagger. The algorithm used to build the classification model on the training data is Support Vector Machine. The unigram feature used is unigram with TFIDF valuation. Classification implementation obtained 86,81 % of accuracy at test of 7-fold cross validation for the type of Sigmoid kernel. Manual class labeling with POS tagger gained 81,67 % of accuracy