Sentimen Analisis Masyarakt terhadap Kasus Penembakan Brigadir J Menggunakan Algoritma Naïve Bayes Classifier

Febby Apri Wenando; Regiolina Hayami; Soni Soni; Ananda Fitria; Deyola Shifana

doi:10.37859/coscitech.v4i2.5686

Febby Apri Wenando Universitas Andalas
Regiolina Hayami Universitas Muhammadiyah Riau
Soni Soni Universitas Muhammadiyah Riau
Ananda Fitria Universitas Andalas
Deyola Shifana Universitas Andalas

https://doi.org/10.37859/coscitech.v4i2.5686

Keywords: Sentiment Analysis, Naïve Bayes, Machine Learning, Twitter

Abstract

Sentiment analysis is computational research of textually expressed opinions, sentiments, and emotions using grouping methods to produce positive or negative assessments. This analysis process generally begins with data collection, which is then processed through a machine learning approach. One of the data collection techniques is using the internet and other social media platforms. One type of social media platform that is currently growing is Twitter. Twitter social media makes it easier for people to express opinions through tweets, commonly called tweets, freely. Netizens can freely express their opinions on any topic, including perceptions of criminal cases in Indonesia. One of the latest cases, which is currently a hot topic of conversation, is the murder case of Brigadier Joshua and the suspect, Inspector General of Police Ferdy Sambo. So, in this research, public opinion on the Twitter platform can be used as material for sentiment analysis to determine public opinion regarding the Ferdy Sambo case. The data used consisted of 234 tweets data with a positive opinion percentage of 51.50% and a negative opinion of 48.50%, which was then classified using the Naive Bayes Classifier Algorithm with the results obtained with an f1-score of 75%.

Downloads

Download data is not yet available.

References

[1] D. Darwis, E. S. Pratiwi, and A. F. O. Pasaribu, “DATA TWITTER KOMISI PEMBERANTASAN KORUPSI REPUBLIK INDONESIA,” J. Ilm. Edutic, vol. 7, no. 1, pp. 1–11, 2020.
[2] Kemenkominfo. “Pengguna Internet di Indonesia 63 Juta Orang”. from kominfo : https://www.kominfo.go.id/content/detail/3415/kominfo-pengguna-internet-di-indonesia-63-juta-orang/0/berita_satker. 2019. [Accessed:Maret 2019].
[3] B. Pang, L. Lee, Opinion Mining and Sentiment Analysis, Foundations and Trends in Information Retrieval, Vol. 2, No 1-2 pp. 1–135, 2008.
[4] Ayu Rizaty, Monavia , Pengguna Twitter di Indonesia Capai 18,45 Juta pada 2022, Available from : .https://dataindonesia.id/digital/detail/pengguna-twitter-di-indonesia-capai-1845-juta-pada-2022
[5] P. Antinasari, R. S. Perdana, and M. A. Fauzi, “Analisis Sentimen Tentang Opini Film Pada Dokumen Twitter Berbahasa Indonesia Menggunakan Naive Bayes Dengan Perbaikan Kata Tidak Baku,” vol. 1 No.12, pp. 1733–1741, 2017.
[6] Wenando, F. A., & Fuad, E. (2019). Detection of Hate Speech in Indonesian Language on Twitter Using Machine Learning Algorithm. Prosiding CELSciTech, 4, 6-8.
[7] H. Annur, “Klasifikasi Masyarakat Miskin Menggunakan Metode Naive Bayes,” Ilk. J. Ilm., vol. 10, no. 2, pp. 160–165, 2018, doi: 10.33096/ilkom.v10i2.303.160-165.
[8] Han, J., and M.Kamber. 2006. Data Mining Concept and Techniques Second Edition. San Frasisco : Elsevier.
[9] Tala, Fadillah Z, A Study of Stemming Effects on Information Retrieval in Bahasa Indonesia, Master of Logic ProjectInstitute for Logic, Language and Computation Universiteit van AmsterdamThe Netherlands, 2003
[10] Wenando, F. A., Hayami, R., & Novermahakim, A. Y. (2020, October). Tweet Sentiment Analysis for 2019 Indonesia Presidential Election Results using Various Classification Algorithms. In 2020 1st International Conference on Information Technology, Advanced Mechanical and Electrical Engineering (ICITAMEE) (pp. 279-282). IEEE.
[11] D. Alita, Y. Fernando, and H. Sulistiani, “Implementasi Algoritma Multiclass SVM pada Opini Publik Berbahasa Indonesia di Twitter,” J. Tekno Kompak, vol. 14, no. 2, pp. 86–91, 2020
[12] Wenando, F. A., Hayami, R., & Anggrawan, A. J. (2020). Analisis Sentimen Pada Pemerintahan Terpilih Pada Pilpres 2019 Ditwitter Menggunakan Algoritme Naïvebayes. JURTEKSI (Jurnal Teknologi dan Sistem Informasi), 7(1), 101-106.
[13] Wildan, M. (2023). Sentimen negatif netizen dalam kolom komentar detik. com terhadap pemberitaan kasus Ferdy Sambo. LITERA, 22(1).
[14] Bayhaqy, A., et al. 2018. "Sentiment Analysis about E-Commerce from Tweets Using Decision Tree, K-Nearest Neighbor, and Naive Bayes". International Conference on Orange Technologies, ICOT 1–6.
[15] Salam, A., Zeniarja, J., Khasanah, RSU. 2018. "Analisis Sentimen Data Komentar Sosial Media Facebook Dengan K-Nearest Neighbor (Studi Kasus Pada Akun Jasa Ekspedisi Barang J&T Ekpress Indonesia)". Prosiding SINTAK. 480.
[16] Wenando, F. A., Septiadi, R., Gunawan, R., & Mukhtar, H. (2022). K-Nearest Neighbor (KNN) untuk Menganalisis Sentimen terhadap Kebijakan Merdeka Belajar Kampus Merdeka pada Komentar Twitter. Jurnal CoSciTech (Computer Science and Information Technology), 3(2), 152-158.
[17] Lisa, R. L. Analisis Sentimen Opini Masyarakat terhadap Institusi Polri pada Media Sosial Twitter menggunakan Metode Support Vector Machine dan Naive Bayes.