Analysis Of Twitter Sentiment Using The Classification Of Naive Bayes Method About Television In Indonesia

Abstract

Television is one of the most widely used electronic mass media in Indonesia. This is because it is easy and inexpensive to be able to watch television broadcasts. Accompanied by the rapid development of the television industry from day to day, causing each television station to compete to present various kinds of shows. Twitter as a micro blog-based social media, is also used by the television industry for publication media, besides that it is also a mouthpiece for criticism and public advice on the programs being aired. Indonesian society with a large number is directly proportional to the number of tweets about television topics in Indonesia. This can be a difficult problem if the assessment data in the form of tweets from the community is still processed manually to produce information regarding the evaluation of television shows. To that end, the authors propose to analyze the data of tweets using an application with a naive Bayes algorithm to be able to produce information on public sentiment assessment regarding television shows. This application is designed using the Python language and PHP. The accuracy value obtained in this study is 91.67%.