Irza Ramira Putra, . (2022) PENGARUH SELEKSI FITUR PARTICLE SWARM OPTIMIZATION TERHADAP SENTIMEN ANALISIS APLIKASI PEDULILINDUNGI DI TWITTER DENGAN ALGORITMA SUPPORT VECTOR MACHINE. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (183kB) |
|
Text
AWAL.pdf Download (605kB) |
|
Text
BAB 1.pdf Download (273kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (374kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (385kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (875kB) |
|
Text
BAB 5.pdf Download (271kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (245kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (173kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (559kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (7MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (824kB) |
Abstract
PeduliLindungi is an application aimed at the public to prevent and deal with COVID-19 in Indonesia. This application must be owned by the Indonesian people, as one of the obligations made by the government from the legislation made to enter public facilities. Of course, this application also certainly brings some feedback from the community. The response can be expressed through quite popular social media such as twitter. Through twitter, they are free to express their opinion about using the application. This study intends to obtain sentiment information related to public opinion related to the use of the PeduliLindungi application, by applying the Support Vector Machine algorithm with the Radial Basis Function kernel and the feature selection Particle Swarm Optimization algorithm in classifying public opinion on the PeduliLindungi application from the tweet data that has been obtained and labelled sentiment as positive and negative. The Support Vector Machine model produces accuracy of 76.24%, recall (sensitivity) of 82.14%, precision of 76.67% and specificity of 68.89%, while the Support Vector Machine model with the Particle Swarm Optimization feature selection increases accuracy to 88.12%, recall (sensitivity) to 96.43%, precision to 84.36% and specificity to 77.78%
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 1810511100] [Pembimbing 1: Yuni Widiastiwi] [Pembimbing 2: Nurul Chamidah] [Penguji 1: Iin Ernawati] [Penguji 2: Helena Nurramdhani Irmanda] |
| Uncontrolled Keywords: | Sentiment Analysis, PeduliLindungi, Twitter, Support Vector Machine, Particle Swarm Optimization |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > T Technology (General) Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | Irza Ramira Putra |
| Date Deposited: | 12 Aug 2022 03:11 |
| Last Modified: | 12 Aug 2022 03:11 |
| URI: | http://repository.upnvj.ac.id/id/eprint/19833 |
Actions (login required)
 |
View Item |