Sheila Gabriela Barus, . (2022) KLASIFIKASI SENTIMEN DATA TIDAK SEIMBANG MENGGUNAKAN ALGORITMA SMOTE DAN K-NEAREST NEIGHBOR PADA ULASAN PENGGUNA APLIKASI PEDULILINDUNGI. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (10kB) |
|
Text
AWAL.pdf Download (424kB) |
|
Text
BAB 1.pdf Download (139kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (221kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (248kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (563kB) |
|
Text
BAB 5.pdf Download (139kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (143kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (16kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (606kB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (616kB) |
Abstract
One of the government's methods in dealing with the spread of Covid-19 that occurred in Indonesia is to create an application, namely the PeduliLindungi application. This application functions in tracking and monitoring the spread of Covid-19, therefore many Indonesian people must have this application. Many reviews are also given on this application, from positive comments to negative comments. These reviews are used as data in this study to determine the results of community sentiment and to test the classification of the K-Nearest Neighbor algorithm. Data collection was done by scraping on google play using the Python programming language, where the data obtained got 750 negative labels and 250 positive labels. So this unbalanced data must be balanced with SMOTE undersampling and oversampling techniques. Therefore, this study carried out three experiments, namely from unbalanced data, data that had been undersampled and data that had been oversampled with SMOTE. The results of the three experiments obtained the best value using the SMOTE technique at K = 1 with an accuracy value of 0.9766, a precision value of 0.9691, an F1 score of 0.9781, a specificity value of 0.9645, and a sensitivity value of 0.9874.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil : 1810511072] [Pembimbing 1 : Didit Widiyanto] [Pembimbing 2 : Mayanda Mega Santoni] [Penguji 1 : Henki Bayu Seta] [Penguji 2 : Desta Sandya Prasvita] |
| Uncontrolled Keywords: | Sentimen, K-Nearest Neighbor, SMOTE, PeduliLindungi |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | Sheila Gabriela Barus |
| Date Deposited: | 10 Aug 2022 06:28 |
| Last Modified: | 10 Aug 2022 06:28 |
| URI: | http://repository.upnvj.ac.id/id/eprint/19804 |
Actions (login required)
 |
View Item |