Fadhillah, Alvyan Arif (2021) Analisis Opini Masyarakat Mengenai Program Bantuan Siswa Dari Pemerintah Kota Surabaya Menggunakan Naïve Bayes Classifier. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 10611710000047-Non_Degree.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
10611710000047-Non_Degree.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (1MB) | Request a copy |
|
Text
10611710000047-Non_Degree.pdf Restricted to Repository staff only Download (1MB) | Request a copy |
Abstract
Saat ini pihak BAPPEKO masih melakukan pengelompokan opini masyarakat terhadap kebijakan Pemerintah secara manual yaitu menilai opini mengelompokan opini masyarakat kedalam kelompok respon positif atau negatif secara subjektif,. Kelemahan metode ini adalah, memakan banyak waktu. Analisis sentimen dengan metode Naïve Bayes Classifier (NBC) dapat menjadi metode pengelompokkan alternatif. Metode ini lebih cepat dan cukup akurat. Permasalahnya yaitu bagaimana hasil pengelompokkan opini masyarakat kedalam respon negatif dan positif dengan menggunakan metode ini?, Penelitian ini bertujuan untuk mengelompokkan opini masyarakat yang mana memberikan respon positif atau negatif. Dengan menggunakan analisis sentimen diperoleh 52% masyarakat beropini poisitif dan 48% masyarakat Surabaya beropini negatif terhadap kebijakan program Pemkot dengan nilai ketepatan klasifikasi menggunakan NBC sebesar 85,86% dan dengan Analisis Cluster terdapat 2 kelompok kecamatan yang terbentuk yaitu kelompok kecamatan bersentimen positif dan negatif.
=====================================================================================================
Currently BAPPEKO is still grouping public opinion on
government policies manually, namely assessing opinions, grouping
public opinion into positive or negative response groups subjectively.
The downside of this method is that it takes a lot of time. Sentiment
analysis using the Naïve Bayes Classifier (NBC) method can be an
alternative grouping method. This method is faster and quite
accurate. The problem is how are the results of grouping public
opinion into negative and positive responses using this method? This
study aims to classify public opinion which gives a positive or
negative response. By using sentiment analysis, it was obtained that
52% of the people had a positive opinion and 48% of the people of
Surabaya had a negative opinion on the program policies of the City
Government with a classification accuracy value using NBC of
85.86% and with Cluster Analysis there were 2 sub-district groups
formed, namely the positive and negative sentiment sub-district
group
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Uncontrolled Keywords: | Sentiment analysis, Clustering analysis, NBC, Community Opinion, Analisis Sentimen, Analisis Cluster, NBC, Opini Masyarakat |
| Subjects: | Q Science > Q Science (General) > Q325.5 Machine learning. |
| Divisions: | Faculty of Vocational > 49501-Business Statistics |
| Depositing User: | Alvyan Arif Fadhillah |
| Date Deposited: | 24 Aug 2021 03:43 |
| Last Modified: | 24 Aug 2021 03:43 |
| URI: | http://repository.its.ac.id/id/eprint/89163 |
Actions (login required)
 |
View Item |