JURNAL RISET INFORMATIKA Vol. 5, No. 1. December 2022 P-ISSN: 2656-1743 |E-ISSN: 2656-1735 DOI: https://doi.org/10.34288/jri.v5i1.481 Accredited rank 3 (SINTA 3), excerpts from the decision of the Minister of RISTEK-BRIN No. 200/M/KPT/2020 529 SUPPORT VECTOR CLASSIFICATION WITH HYPERPARAMETERS FOR ANALYSIS OF PUBLIC SENTIMENT ON DATA SECURITY IN INDONESIA Siti Ernawati -1*) , Risa Wati -2 , Nuzuliarini Nuris -3 Sistem Informasi Universitas Nusa Mandiri Jakarta, Indonesia www.nusamandiri.ac.id 1*) siti.ste@nusamandiri.ac.id Sistem Informasi Universitas Bina Sarana Informatika Jakarta, Indonesia www.bsi.ac.id 2 risawati.rwx@bsi.ac.id, 3 nuzuliarini.nzn@bsi.ac.id (*) Corresponding Author Abstract The development of Information Technology makes increasing use of the internet. This raises the vulnerability of data security. Cyber attacks in Indonesia caused many tweets on social media Twitter. Some are positive, and some are negative. The problem of this study is to determine the public sentiment towards data security in Indonesia, while the purpose of this study is how the response or evaluation of the government of Indonesia to the many perceptions of people who lack confidence in data security in Indonesia. Data obtained from twitter with as much as 706 data was processed using python with a percentage of 10% test data and 90% training data. Weighting is done using TF-IDF, and then the data is processed using the Support Vector Machine algorithm using the SVC (Support Vector Classification) library. Support Vector Classification with RBF kernel classifies Text well to obtain AUC value with good classification category. Utilizing one of the hyperparameter techniques, which is a grid search technique that can compare the accuracy of test results. The test results using SVC with RBF kernel obtained an accuracy value of 0.87, Precision of 0.82, recall of 0.94, and F1_Score of 0.87. This study is expected to be used by decision-makers related to public confidence in data security in Indonesia. Keywords: Data Security; Grid Search ; Hyperparameter; SVC Abstrak Berkembangnya teknologi Informasi membuat meningkatnya penggunaan internet. Hal ini menimbulkan rentannya keamaan data. Serangan siber di Indonesia menimbulkan banyaknya cuitan pada media social twitter, ada yang beropini positif dan ada yang beropini negative. Permasalahan dalam penelitian adalah untuk mengetahui sentimen masyarakat terhadap keamanan data di Indonesia, sedangkan tujuan dari penelitian ini adalah bagaimana tanggapan atau evaluasi pemerintah Indonesia terhadap banyaknya persepsi masyarakat yang kurang percaya terhadap keamanan data di Indonesia. Data diperoleh dari twitter dengan jumlah data sebanyak 706 data diolah menggunakan python dengan prosentase 10% data test dan 90% data training. Dilakukan pembobotan menggunakan TF-IDF selanjutnya data diolah menggunakan algoritma Support Vector Machine dengan memanfaatkan library SVC (Support Vector Classification). Support Vector Classification dengan kernel RBF mengklasifikasikan teks dengan baik memperoleh nilai AUC dengan kategori good classification. Memanfaatkan salah satu teknik hyperparameter yaitu teknik grid search yang dapat membandingkan keakuratan hasil uji. Hasil uji menggunakan SVC dengan kernel RBF didapatkan nilai akurasi sebesar 0.87, Precision 0.82, recall 0.94 dan F1_Score 0.87. Penelitian ini diharapkan dapat dijadikan pengambil keputusan terkait kepercayaan masyarakat terhadap keamanan data di Indonesia. Kata kunci: Grid Search; Hyperparameter; Keamanan Data; SVC