ANALYSIS OF OIL SENTIMENT SENTIMENTS ON TWITTER USING SUPPORT VECTOR MACHINE

Abstract

Twitter is one of the social media platforms used by people in Indonesia. Twitter is often used by its users to express opinions regarding a product, institution or event. From the keyword fuel, fuel subsidy is a keyword that is currently a trending topic because changes in fuel subsidies affect the prices of other staples, to find out the value of sentiment in public opinion, sentiment analysis is one of the methods used is the support vector machine and lexicon based. Lexicon is a labeling method by matching the words contained in the document with the words contained in the dictionary. After labeling, the data is tested using the classification method, the classification stage is carried out after going through the preprocessing phase, where the tweet classification results tend to be positive or negative, using the Support Vector Machine method and validated by K-Fold Cross Validation.This research produced 50,001 data which were divided into 21,561 positive sentiments, 9206 neutral sentiments and 19234 negative sentiments. From these results it can be concluded that the data shows public support for rising fuel prices or changing fuel subsidy prices.