Penggunaan N-gram pada Analisa Sentimen Pemilihan Kepala Daerah Jakarta Menggunakan Algoritma Naïve Bayes

Indhiarta, Wahyu Candra and , Endang Wahyu Pamungkas, S.Kom, M.Kom. (2017) Penggunaan N-gram pada Analisa Sentimen Pemilihan Kepala Daerah Jakarta Menggunakan Algoritma Naïve Bayes. Diploma thesis, Universitas Muhammadiyah Surakarta.

	PDF (Naskah Publikasi) NASKAH PUBLIKASI.pdf Download (1MB)
	PDF (Pernyataan Publikasi Ilmiah) Surat Pernyataan Publikasi.pdf Restricted to Repository staff only Download (569kB) | Request a copy

Abstract

In the current era of globalization of the Internet is very rapid development, because the human need for the internet is always evolving and rapid technological advancement. Most people use the internet to access social media, one of which is social media twitter. Many people who express their wishes or opinions on social media twitter is both positive and negative opinions. Opinions from this community can be used as research to obtain an information. The result of such information in its utilization requires proper analysis so as to provide support in determining a decision. Sentiment analysis is a data processing technique that can solve the problem well. Sentiment analysis was used in this study to see the opinion of the public against the election of the Jakarta regional head on social media twitter. This study used the Naïve Bayes algorithm to classify opinions to be positive or negative by using the selection of features of Chi Square that have been done N-gram before. The purpose of this research is to see the level of classification accuracy using Naïve Bayes algorithm by using N-gram feature.

Item Type:	Karya ilmiah (Diploma)
Uncontrolled Keywords:	Analisa Sentimen, N-gram, Naïve Bayes.
Subjects:	T Technology > T Technology (General) T Technology > TN Mining engineering. Metallurgy
Divisions:	Fakultas Ilmu Komunikasi dan Informatika > Teknik Informatika
Depositing User:	WAHYU CANDRA INDHIARTA
Date Deposited:	10 Aug 2017 07:39
Last Modified:	10 Aug 2017 07:39
URI:	http://eprints.ums.ac.id/id/eprint/55077

Actions (login required)

View Item