PDF Get rights and content
OriginalPaper | Open access | Published: July 31, 2024

Sentiment Analysis Against Rohingya Immigrants On Twitter Using The Support Vector Machine Method

Lailatul Husna Aulia, Sriani
JINAV: Journal of Information and Visualization, Vol. 5 No. 1 (2024), pp. 97-106 https://doi.org/10.35877/454RI.jinav2775 Published: 2024-07-31
Get Permissions

Abstract

The influx of Rohingya migrants into Indonesia has sparked diverse reactions from the public, ranging from both positive and negative perspectives. These viewpoints have surfaced prominently on Twitter, where netizens express conflicting opinions that often lead to division and discord. This study seeks to examine the sentiment of public opinion regarding Rohingya immigrants on Twitter, employing a Support Vector Machine with RBF kernel implemented in Python as its analytical method. The sentiment resulting from the crawling process on Twitter was 1347 pieces of data. In the analysis, the comparison between training data and test data was 8: 2. The dataset after preprocessing consisted of 1321 data, 1056 of which were training data while 265 were test data. The results of sentiment analysis show that the SVM method can be used to analyze sentiment, the accuracy value obtained is 72%, precision is 100%, recall is 2%, and f1-Score is 3%.

Keywords

Sentiment AnalysisRohingyaTwitterSupport Vector Machine

References (11)

  1. Ariansyah, A., & Kusmira, M. (2021). Analisis Sentimen Pengaruh Pembelajaran Daring Terhadap Motivasi Belajar Di Masa Pandemi Menggunakan Naive Bayes Dan Svm. Faktor Exacta, 14(3), 100. https://doi.org/10.30998/faktorexacta.v14i3.10325
  2. Dhea Nada, T. gunawan. (2021). Peran Pemerintah Dalam Menangani Pengungsi Rohingya Di Kota Lhokseumawe (Studi pada Kantor Imigrasi Kelas II TPI kota Lhokseumawe) Dhea. Kajian Administrasi Negara: Riset Dan Pengabdian, 01(01), 45–50.
  3. Giovani, A. P., Haryanti, T., & Kurniawati, L. (2020). Analisis Sentimen Aplikasi Ruang Guru Di Twitter Menggunakan Algoritma Klasifikasi. 14(2), 116–124.
  4. Hermawan, L., & Bellaniar Ismiati, M. (2020). Pembelajaran Text Preprocessing berbasis Simulator Untuk Mata Kuliah Information Retrieval. Jurnal Transformatika, 17(2), 188. https://doi.org/10.26623/transformatika.v17i2.1705
  5. Ismail, A. R., Bagus, R., & Hakim, F. (2023). Implementasi Lexicon Based Untuk Analisis Sentimen Dalam Mengetahui Trend Wisata Pantai Di DI Yogyakarta Berdasarkan Data Twitter. 1(1), 37–46.
  6. Moch Arifqi Ramadhan, R. A. (2022). Klasifikasi Text Spam Menggunakan Metode Support Vector Machine Dan Naive Bayes (R. M. Awangga (ed.)). Penerbit Buku Pedia.
  7. Que, V. K. S., Iriani, A., & Purnomo, H. D. (2020). Analisis Sentimen Transportasi Online Menggunakan Support Vector Machine Berbasis Particle Swarm Optimization. Jurnal Nasional Teknik Elektro Dan Teknologi Informasi, 9(2), 162–170. https://doi.org/10.22146/jnteti.v9i2.102
  8. Rosyida, T., Putro, H. P., Wahyono, H., Teknik, F., & Krisnadwipayana, U. (2024). Opini Dari Twitter Menggunakan Naïve Bayes Dan Svm. 26(1).
  9. Sriani, Suhardi, I. F. G. (2023). Analisis Sentimen Kebijakan Pemberian Subsidi Motor Listrik Menggunakan Metode Support Vector Machine. 13(3), 511–517.
  10. Yulian Azhari, W. (2022). Pencegahan Potensi Konflik Antara Pengungsi Rohingya Dan Masyarakat Lokal Indonesia. Pengabdian Mandiri, 20(1), 105–123.

How to Cite

Aulia, L. H., & Sriani, S. (2024). Sentiment Analysis Against Rohingya Immigrants On Twitter Using The Support Vector Machine Method. JINAV: Journal of Information and Visualization, 5(1), 97–106. https://doi.org/10.35877/454RI.jinav2775