Analisis Sentimen dan Klasifikasi Terhadap Tren “UU ITE” di Media Sosial Twitter

Risky  Setyadi Putra; Muhammad  Habibi; Aris  Wahyu Murdiyanto; Nafisa Alfi Sa'diya

doi:10.30989/teknomatika.v14i2.1116

Risky Setyadi Putra Universitas Jenderal Achmad Yani Yogyakarta
Muhammad Habibi Universitas Jenderal Achmad Yani Yogyakarta
Aris Wahyu Murdiyanto Universitas Jenderal Achmad Yani Yogyakarta
Nafisa Alfi Sa'diya Universitas Jenderal Achmad Yani Yogyakarta

DOI: https://doi.org/10.30989/teknomatika.v14i2.1116

Abstract

Undang-undang Informasi and Transaksi Elektronik abbreviated UU ITE is a law that regulates information and electronic transactions, or information technology in general. This study discusses sentiment analysis from tweet data with keywords “UU ITE” Who uses as much data 7.407 tweet data and re-tweets taken in the period July 21 - August 16, 2021, with details 914 data that has been manually labeled and 6,493 data labeled using Predicting that the data was taken using authentication on the Twitter API and executed using the Python library. This research uses methods Support Vector Machine because it has several advantages including It is capable of handling the classification of two classes, and its implementation is relatively easy. For the support vector machine stage, namely data retrieval, preprocessing data, manual labeling, data training and testing. As for the solution offered in this research is to create an analysis model that can be used to conduct sentiment analysis about the ITE Law on social media Twitter. This research was successful using the Support Vector Machine method to create a sentiment analysis model with an accuracy of 81.20% for data Training and 87% for data testing. This study provides results that UU ITE have negative sentiments by netizens on social media Twitter based on on the results of classification and calculations on the model and tweet data and the number of Negative discussions.

References

[1] F. D. Ananda and Y. Pristyanto, “Analisis Sentimen Pengguna Twitter Terhadap Layanan Internet Provider Menggunakan Algoritma Support Vector Machine,” MATRIK J. Manajemen, Tek. Inform. dan Rekayasa Komput., vol. 20, no. 2, pp. 407–416, May 2021, doi: 10.30812/matrik.v20i2.1130.

[2] V. M. Rumata, “Analisis Isi Kualitatif Twitter ‘#TaxAmnesy’ dan ‘#AmnestiPajak,’” J. PIKOM (Penelitian Komun. dan Pembangunan), vol. 18, no. 1, p. 1, Aug. 2017, doi: 10.31346/jpikom.v18i1.840.

[3] B. Andrianto, “Analisis Sentimen Konten Radikal Melalui Dokumen Twitter Menggunakan Metode Backpropagation,” 2018.

[4] A. Novantirani, M. K. . Sabariah, and V. Effendy, “Analisis Sentimen pada Twitter untuk Mengenai Penggunaan Transportasi Umum Darat Dalam Kota dengan Metode Support Vector Machine,” E-Proceeeding Eng., vol. 2 No.1, pp. 1–7, 2015.

[5] Dinda Tri Wisudawati and P. R. A. Tiani Wahyu Utami, “Analisis Sentimen Terhadap Dampak Covid-19 Pada Performa Tokopedia Menggunakan Support Vector Machine,” 2020.

[6] Anto Satriyo Nugroho, “Support Vector Machine,” 2003.

[7] F. D. Ananda, “Analisis Sentimen Pengguna Twitter Terhadap Layanan Internet Provider Menggunakan Algoritma Support Vector Mechine,” 2021.

[8] S. N. I. S. D and S. M. D. HUTABARAT, “Pendampingan Penggunaan Media Sosial Yang Cerdas Dan Bijak Berdasarkan Undang-Undang Informasi Dan Transaksi Elektronik,” Disem. J. Pengabdi. Kpd. Masy., vol. 2, no. 1, pp. 34–46, Mar. 2020, doi: 10.33830/diseminasiabdimas.v2i1.754.

[9] Hidayatullah, “Analisis Sentimen Dan Klasifikasi Kategori Terhadap Tokoh Publik Pada Twitter,” 2014.

[10] P. A. Octaviani, “Penerapan Metode Klasifikasi Support Vector Machine (Svm) Pada Data Akreditasi Sekolah Dasar (Sd) di Kabupaten 40 Magelang,” 2014.