KLASIFIKASI SENTIMEN DATA TIDAK SEIMBANG MENGGUNAKAN ALGORITMA SMOTE DAN K-NEAREST NEIGHBOR PADA ULASAN PENGGUNA APLIKASI PEDULILINDUNGI

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 app...

Full description

Saved in:
Bibliographic Details
Main Author: Sheila Gabriela Barus, (Author)
Format: Book
Published: 2022-07-11.
Subjects:
Online Access:Link Metadata
Tags: Add Tag
No Tags, Be the first to tag this record!

MARC

LEADER 00000 am a22000003u 4500
001 repoupnvj_19804
042 |a dc 
100 1 0 |a Sheila Gabriela Barus, .  |e author 
245 0 0 |a KLASIFIKASI SENTIMEN DATA TIDAK SEIMBANG MENGGUNAKAN ALGORITMA SMOTE DAN K-NEAREST NEIGHBOR PADA ULASAN PENGGUNA APLIKASI PEDULILINDUNGI 
260 |c 2022-07-11. 
500 |a http://repository.upnvj.ac.id/19804/1/ABSTRAK.pdf 
500 |a http://repository.upnvj.ac.id/19804/2/AWAL.pdf 
500 |a http://repository.upnvj.ac.id/19804/3/BAB%201.pdf 
500 |a http://repository.upnvj.ac.id/19804/4/BAB%202.pdf 
500 |a http://repository.upnvj.ac.id/19804/5/BAB%203.pdf 
500 |a http://repository.upnvj.ac.id/19804/6/BAB%204.pdf 
500 |a http://repository.upnvj.ac.id/19804/7/BAB%205.pdf 
500 |a http://repository.upnvj.ac.id/19804/8/DAFTAR%20PUSTAKA.pdf 
500 |a http://repository.upnvj.ac.id/19804/9/RIWAYAT%20HIDUP.pdf 
500 |a http://repository.upnvj.ac.id/19804/10/LAMPIRAN.pdf 
500 |a http://repository.upnvj.ac.id/19804/11/HASIL%20PLAGIARISME.pdf 
500 |a http://repository.upnvj.ac.id/19804/12/ARTIKEL%20KI.pdf 
520 |a 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. 
546 |a id 
546 |a id 
546 |a id 
546 |a id 
546 |a id 
546 |a id 
546 |a id 
546 |a id 
546 |a id 
546 |a id 
546 |a id 
546 |a id 
690 |a QA75 Electronic computers. Computer science 
690 |a QA76 Computer software 
655 7 |a Thesis  |2 local 
655 7 |a NonPeerReviewed  |2 local 
787 0 |n http://repository.upnvj.ac.id/19804/ 
787 0 |n http://repository.upnvj.ac.id 
856 4 1 |u http://repository.upnvj.ac.id/19804/  |z Link Metadata