Information System Based on Sentiment Analysis: Study of the Application of Naive Bayes Classifier to Service Provider 3 on Twitter

Akhmad Chanafi, Muhammad Arifin, Arif Setiawan

Abstract


Twitter is used to exchange information, opinions on a topic circulating in the community. Of course, this can be used to find out what the public thinks about a product or hot news. With the Twitter social media, the information obtained is very diverse through tweets, the tweets themselves are written information in the form of raw data that can be processed into sentiment analysis. The data obtained and processed in this study is Twitter data with the keyword triindonesia. The data will be divided into training data and test data and classified into 3 classes namely positive, neutral and negative using the Naïve Bayes classifier method. In the implementation of the test, the use of SMOTE is needed to overcome data imbalance, because the data obtained is not balanced. After going through 3 tests with different distribution of data sets, the highest accuracy value was obtained at 79% in the distribution of 90% training data and 10% testing data.

Keywords


Sentiment analysis, Twitter, TriIndonesia, Naïve Bayes Classifier, SMOTE

Full Text:

PDF

References


S. Kemp, “Digital 2022: Indonesia — DataReportal – Global Digital Insights,” Global Digital Insights. pp. 1–103, 2022, Accessed: Mar. 14, 2023. [Online]. Available: https://datareportal.com/reports/digital-2022-indonesia. [2] M. Ghifari et al., “ANALISIS SENTIMEN TWITTER TERHADAP KENAIKAN BAHAN SENTIMENT ANALYSIS OF TWITTER ON FUEL OIL INCREASE USING,” vol. 2, no. April, pp. 219–226, 2023. [3] M. I. Fikri, T. S. Sabrila, and Y. Azhar, “Perbandingan Metode Naïve Bayes dan Support Vector Machine pada Analisis Sentimen Twitter,” SMATIKA J., vol. 10, no. 02, pp. 71–76, 2020, doi: 10.32664/smatika.v10i02.455. [4] “5 Operator Seluler Favorit Masyarakat Indonesia Versi APJII.” https://databoks.katadata.co.id/datapublish/2022/06/13/5-operator-seluler-favorit-masyarakat-indonesia-versi-apjii (accessed Mar. 15, 2023). [5] V. Amrizal, “Penerapan Metode Term Frequency Inverse Document Frequency (Tf-Idf) Dan Cosine Similarity Pada Sistem Temu Kembali Informasi Untuk Mengetahui Syarah Hadits Berbasis Web (Studi Kasus: Hadits Shahih Bukhari-Muslim),” J. Tek. Inform., vol. 11, no. 2, pp. 149–164, 2018, doi: 10.15408/jti.v11i2.8623. [6] F. Ratnawati, “Implementasi Algoritma Naive Bayes Terhadap Analisis Sentimen Opini Film Pada Twitter,” INOVTEK Polbeng - Seri Inform., vol. 3, no. 1, p. 50, 2018, doi: 10.35314/isi.v3i1.335. [7] A. Rahman Isnain, A. Indra Sakti, D. Alita, and N. Satya Marga, “Sentimen Analisis Publik Terhadap Kebijakan Lockdown Pemerintah Jakarta Menggunakan Algoritma Svm,” Jdmsi, vol. 2, no. 1, pp. 31–37, 2021, [Online]. Available: https://t.co/NfhnfMjtXw. [8] A. D. Adhi Putra, “Analisis Sentimen pada Ulasan pengguna Aplikasi Bibit Dan Bareksa dengan Algoritma KNN,” JATISI (Jurnal Tek. Inform. dan Sist. Informasi), vol. 8, no. 2, pp. 636–646, 2021, doi: 10.35957/jatisi.v8i2.962. [9] M. Chalida and M. D. R. Wahyudi, “Analisis Sentimen Ujaran Kebencian Pemilihan Presiden 2019 Menggunakan Algoritma Naïve Bayes (Studi Kasus: Tweet #Pilpres2019 Di Kota Jakarta, Bandung, Semarang, Surabaya Dan Yogyakarta),” Jnanaloka (Jurnal Open Access Yayasan Lentera Dua Indones., no. 2001, pp. 5–10, 2019. [10] N. M. A. J. Astari, Dewa Gede Hendra Divayana, and Gede Indrawan, “Analisis Sentimen Dokumen Twitter Mengenai Dampak Virus Corona Menggunakan Metode Naive Bayes Classifier,” J. Sist. dan Inform., vol. 15, no. 1, pp. 27–29, 2020, doi: 10.30864/jsi.v15i1.332. [11] M. A. F. Umi Rofiqoh1, Rizal Setya Perdana2 and Program, “Analisis Sentimen Tingkat Kepuasan Pengguna Penyedia Layanan Telekomunikasi Seluler Indonesia Pada Twitter dengan Metode Support Vector Machine dan Lexicon Based Features Twitter event detection View project Human Detection and Tracking View project,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 1(12), no. October, pp. 1725–1732, 2017, [Online]. Available: https://www.researchgate.net/publication/320234928. [12] E. S. Negara, R. Andryani, and P. H. Saksono, “Analisis Data Twitter: Ekstraksi dan Analisis Data G eospasial,” J. INKOM, vol. 10, no. 1, p. 27, 2016, doi: 10.14203/j.inkom.433. [13] A. Rossi, T. Lestari, R. Setya Perdana, and M. A. Fauzi, “Analisis Sentimen Tentang Opini Pilkada Dki 2017 Pada Dokumen Twitter Berbahasa Indonesia Menggunakan Naïve Bayes dan Pembobotan Emoji,” Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 1, no. 12, pp. 1718–1724, 2017, [Online]. Available: http://j-ptiik.ub.ac.id. [14] I. H. Witten, M. A. Hall, and E. Frank, “Data Mining: Practical Machine Learning Third Edition,” (Morgan Kaufmann Ser. Data Manag. Syst. Morgan Kaufmann, vol. 104, no. June, p. 113, 2005.




DOI: https://doi.org/10.24176/insytech.v1i2.14606

Refbacks

  • There are currently no refbacks.