Uji Kernel SVM dalam Analisis Sentimen Terhadap Layanan Telkomsel di Media Sosial Twitter

Abstract

Telkomsel is an internet service provider in Indonesia which was launched in 1995. As an internet 
 service provider with the most users, Telkomsel has become the center of attention of internet users in Indonesia. This 
 invites user opinions and perspectives on Telkomsel, which is commonly referred to as sentiment. One of the media 
 commonly used to express an opinion and point of view is Twitter. Twitter is a social media platform that is often a 
 place for sharing and spreading the news, and discussing ideas, and opinions of Twitter users. In this study, the algorithm used 
 is the Support Vector Machine. In the Support Vector Machine, there is a kernel trick that will be used to determine 
 kernel performance and analyze sentiment. The sentiments analyzed amounted to 537 tweets collected by scraping. 
 The collected tweets will go through the preprocessing stage, namely cleaning, case folding, tokenizing, normalization, 
 stemming, stopword removal, and detokenizing. A sentiment is classified into 2 labels, namely positive and negative. 
 Based on the test results, the sigmoid kernel has the best performance with an accuracy value of 0.950, a precision of 
 0.945, a recall of 0.860, an f1-score of 0.896, and sentiment tend toward negative.