Isyqi, Ahmad Bihar (2021) Implementasi Text Mining pada Analisis Sentimen Pengguna Twiter terhadap Kebijakan Penanganan COVID-19 di Indonesia menggunakan Metode Regresi Logistik dan Support Vector Machine. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 06211740000110-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
06211740000110-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (1MB) | Request a copy |
Abstract
Penanganan COVID-19 merupakan salah satu masalah kompleks yang dihadapi Indonesia. Pemerintah meresponnya dengan menanganinya melalui berbagai kebijakan, sehingga kebijakan yang dikeluarkan kerap mendapat respon publik di media sosial. Penelitian ini dilakukan untuk mengetahui tanggapan masyarakat berdasarkan sentimen di media sosial Twitter terhadap kebijakan yang telah ditetapkan pemeritah dalam menangani pandemi COVID-19. Data yang digunakan dalam penelitian ini merupakan hasil crawling data dari tiga kata kunci yaitu, “PPKM”, “wajib masker”, dan “vaksinasi”. Hasil analisis menunjukkan bahwa pengguna Twitter memberikan respon positif terhadap kebijakan yang ditetapkan pemerintah dalam rangka penanganan pandemi. Kemudian dari hasil klasifikasi menggunakan Regresi Logistik Biner dan Support Vector Machine didapatkan bahwa pada data SMOTE menghasilkan nilai AUC yang lebih baik dari pada data awal yang belum melalui proses SMOTE. Lalu, jika metode Regresi Logistik Biner dan Support Vector Machine dibandingkan, dihasilkan bahwa metode terbaik yang cocok digunakan dalam penelitian ini adalah metode SVM dengan Kernel RBF menggunakan parameter (C) 100 dan gamma (γ) 0,1.
===========================================================
===================================
Handling COVID-19 is one of the complex problems facing by Indonesia. The government responds to it by handling it through various policies so that the policy issued often get a public response on social media. This research was conducted to find out the public's response based on the sentiments on Twitter that the government had set in dealing with the COVID-19 pandemic. The data used in this study is the result of crawling data from three keywords "PPKM", "wajib masker", and "vaksinasi". The results of the analysis show that Twitter users give a positive response to the policies set by the government in the context of handling the pandemic. Then from the classification results using Binary Logistics Regression and Support Vector Machine obtained on the SMOTE data, the AUC value is better than the initial data that has not been through the SMOTE process. Then when compared to the Binary Logistics Regression and Support Vector Machine methods, the best method that is suitable for use in this research is the SVM Kernel RBF method with parameters (C) 100 and gamma (γ) 0.1.
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Uncontrolled Keywords: | Analisis Sentimen, Kebijakan Penanganan COVID-19, Regresi Logistik Biner, SVM, SMOTE, Binary Logistics Regression, COVID-19 Handling Policies, Sentiment Analysis, SMOTE, SVM. |
| Subjects: | H Social Sciences > HA Statistics H Social Sciences > HD Industries. Land use. Labor > HD108 Classification (Theory. Method. Relation to other subjects ) Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Ahmad Bihar Isyqi |
| Date Deposited: | 01 Sep 2021 15:16 |
| Last Modified: | 01 Sep 2021 15:16 |
| URI: | http://repository.its.ac.id/id/eprint/91275 |
Actions (login required)
 |
View Item |