ANALISIS SENTIMEN DI MEDIA SOSIAL TWITTER DENGAN STUDI KASUS KARTU PRAKERJA
Abstract
Kartu Prakerja is one of the government's flagship programs in providing training to the workforce. In its implementation there is a lot of information scattered, especially on social media Twitter both in the pros and cons of Kartu Prakerja program. Based on information in the form of tweets that have not been analyzed in depth, it is necessary to analyze sentiment on the Kartu Prakerja in order to obtain appropriate information based on the opinions of netizen s on Twitter. This study discusses sentiment analysis of tweet data with the keyword “Kartu Prakerja” which uses data as many as 6658 tweet data taken in the period May 27 - August 5, 2021. This research uses the Naive Bayes Classification method which has several stages, namely data retrieval, data preprocessing, manual labeling, data training and testing. The solution offered in this study is to create an analysis model that can be used to perform sentiment analysis about Kartu Prakerja on Twitter. Based on the results of this study obtained that the calculation of accuracy obtained a value of 86% for training data and 87% for data testing. This study concluded that the Kartu Prakerja has a positive sentiment by Twitter netizens based on the results of Classification that discusses many positive sentiments such as the benefits, effectiveness and addition of the Kartu Prakerja budget.
References
[2] L. A. Abdillah, “Kartu Prakerja Bantuan Pemerintah di Masa Pandemi Global COVID-19.”
[3] P. Antinasari, R. Setya Perdana, and M. A. Fauzi, “Analisis Sentimen Tentang Opini Film Pada Dokumen Twitter Berbahasa Indonesia Menggunakan Naive Bayes Dengan Perbaikan Kata Tidak Baku,” 2017. [Online]. Available: http://j-ptiik.ub.ac.id
[4] R. N. Devita, H. W. Herwanto, and A. P. Wibawa, “Perbandingan Kinerja Metode Naive Bayes dan K-Nearest Neighbor untuk Klasifikasi Artikel Berbahasa indonesia,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 5, no. 4, p. 427, Oct. 2018, doi: 10.25126/jtiik.201854773.
[5] A. Pandhu and W. Diki, “Analisa sentimen dan Klasifikasi Komentar Positif Pada Twitter dengan Naïve Bayes Classification,” BRITech(Jurnal Ilmiah Komputer, Sains Dan Teknologi Terapan)), Jakarta, vol. 1, no. 2, 2020.
[6] N. Ruhyana, “Analisis Sentimen Terhadap Penerapan Sistem Plat Nomor Ganjil/Genap Pada Twitter Dengan Metode Klasifikasi Naive Bayes.” [Online]. Available: www.situs.com
[7] M. Nur, Y. Utomo, P. Negeri, and U. Pandang, Analisis Sentimen pada Twitter terhadap Pelayanan Pemerintah Kota Makassar. [Online]. Available: https://dev.twitter.com
[8] A. Sentimen Untuk Penilaian Pelayanan Situs Belanja Online Menggunakan Algoritma Naïve Bayes Muljono, D. Putri Artanti, A. Syukur, A. Prihandono, and D. I. Rosal Moses Setiadi, “Konferensi Nasional Sistem Informasi 2018 STMIK Atma Luhur Pangkalpinang,” 2018. [Online]. Available: http://twitter.com
[9] G. A. Buntoro, “Analisis Sentimen Calon Gubernur DKI Jakarta 2017 Di Twitter,” 2017. [Online]. Available: https://t.co/jrvaMsgBdH
[10] R. N. Devita, H. W. Herwanto, and A. P. Wibawa, “Perbandingan Kinerja Metode Naive Bayes dan K-Nearest Neighbor untuk Klasifikasi Artikel Berbahasa indonesia,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 5, no. 4, p. 427, Oct. 2018, doi: 10.25126/jtiik.201854773.
[11] J. Da, C. Aruan, B. Rahayudi, and A. Ridok, “Analisis Sentimen Opini Masyarakat terhadap Pelayanan Rumah Sakit Umum Daerah menggunakan Metode Support Vector Machine dan Term Frequency-Inverse Document Frequency,” 2022. [Online]. Available: http://j-ptiik.ub.ac.id