Anggara, Arda Wahyu Tri (2022) Analisis sentimen pengguna Twitter terhadap kebijakan Kementrian Kesehatan Ri dalam penanganan pandemi Covid-19 menggunakan metode naive bayes classifier dan metode Support Vector Machine. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 106111710000024-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
106111710000024-Undergraduate_Thesis.pdf Restricted to Repository staff only Download (1MB) |
Abstract
Keresahan masyarakat tentang penyebaran COVID-19 membuat banyak pihak terkait mencoba membendung tingkat penyebaran kasus COVID-19, salah satunya adalah Kementerian Kesehatan Republik Indonesia. Kebijakan yang digagas oleh pemerintah menuai polemik dari berbagai pihak dan diaspirasikan melalui media sosial, salah satunya Twitter. Beberapa waktu lalu, isu keresahan masyarakat terhadap kebijakan pemerintah dalam menangani penyebaran COVID-19 ini menjadi _trending topic_ di media sosial Twitter. Komentar-komentar yang disampaikan masyarakat masih bercampur antara komentar yang bersifat membangun dan mengkritik. Sehingga, perlu dilakukan penelitian guna mengetahui sentimen masyarakat terhadap kebijakan Kementerian Kesehatan Republik Indonesia dalam menangani pandemi COVID-19 terhadap kebijakan yang telah dilaksanakan. Proses penelitian diawali dengan mengunduh data dan kemudian melakukan praproses teks guna membersihkan data. Kemudian, untuk analisis klasifikasi data teks akan digunakan metode Naïve Bayes Classifier dan Support Vector Machine untuk melihat tingkat ketepatan hasil klasifikasi. Hasil dari penelitian ini diketahui bahwa sentimen positif sebesar 87% dan sentimen negatif sebesar 13%, sedangkan metode terbaik adalah metode Naïve Bayes Classifier dengan predikat _good classification_. Melalui penelitian ini diharapkan dapat memperbaiki kinerja Kementerian Kesehatan Republik Indonesia terhadap kebijakan penanganan pandemi COVID-19.
=================================================================================================================================
Public concern about the spread of COVID-19 has prompted many related parties to attempt to curb the spread of COVID-19 cases, one of which is the Ministry of Health of the Republic of Indonesia. The policies initiated by the government have sparked controversy among various groups, which has been expressed through social media, one of which is Twitter. Some time ago, public concern regarding government policies in dealing with the spread of COVID-19 became a trending topic on Twitter. The comments made by the public were mixed, consisting of both constructive and critical comments. Therefore, it is necessary to conduct research to determine public sentiment toward the policies of the Ministry of Health of the Republic of Indonesia in dealing with the COVID-19 pandemic and the policies that have been implemented. The research process began by downloading the data and then preprocessing the text to clean the data. Subsequently, the Naïve Bayes Classifier and Support Vector Machine methods were used to analyze the classification of text data and determine the accuracy of the classification results. The results of this study showed that positive sentiment accounted for 87%, while negative sentiment accounted for 13%. The best method was the Naïve Bayes Classifier, which achieved a _good classification_ predicate. Through this research, it is expected that the findings can contribute to improving the performance of the Ministry of Health of the Republic of Indonesia in implementing policies for handling the COVID-19 pandemic.
| Item Type: | Thesis (Other) |
|---|---|
| Additional Information: | 519.53 Ang a-1 |
| Uncontrolled Keywords: | Analisis Sentimen, Kemenkes, Naïve Bayes Classifier ¸ Support Vector Machine, Sentiment Analysis, Kemenkes, Naïve Bayes Classifier ¸ Support Vector Machine |
| Subjects: | Q Science > QA Mathematics > QA278.55 Cluster analysis |
| Divisions: | Faculty of Vocational > 49501-Business Statistics |
| Depositing User: | magang . |
| Date Deposited: | 06 Oct 2026 06:46 |
| Last Modified: | 06 Oct 2026 06:46 |
| URI: | http://repository.its.ac.id/id/eprint/145328 |
Actions (login required)
 |
View Item |