Ghifari Ahmad Lustiansyah, . (2022) ANALISIS KLASIFIKASI SENTIMEN PENGGUNA APLIKASI PEDULINDUNGI BERDASARKAN ULASAN DENGAN MENGGUNAKAN METODE LONG SHORT TERM MEMORY. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (100kB) |
|
Text
AWAL.pdf Download (366kB) |
|
Text
BAB 1.pdf Download (141kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (415kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (228kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (824kB) |
|
Text
BAB 5.pdf Download (129kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (113kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (24kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (9MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (589kB) |
Abstract
The PeduliLindungi application was built for surveillance during the COVID-19 pandemic. This application is used as a container for handling and making it easier for the public when traveling by sharing location data so that tracing contact history with Covid-19 sufferers can be more easily handled and carried out immediately. After this application was released on the Google Play Store, many reviews were commented on by users of this application, ranging from negative comments to positive comments. Therefore, this study will analyses the sentiments of the reviews given by users of the PeduliLindungi application using the Long Short Term Memory method. The use of this method is expected to get high accuracy so that this method can classify negative comments and positive comments to get an evaluation that can improve services to the community through this application. The stages carried out in this study used data preprocessing stages such as case folding, filtering, word normalization, stopword removal, stemming, and tokenization. After that, the data was trained using the LSTM model and obtained an accuracy of 82.44%, precision of 78.66%, and recall of 87.03%.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 1810511048] [Pembimbing 1: Didit Widiyanto] [Pembimbing 2: Bambang Tri Wahyono] [Penguji 1: Bayu Hananto] [Penguji 2: Mayanda Mega Santoni] |
| Uncontrolled Keywords: | PeduliLindungi, Long Short Term Memory, Sentiment Analysis |
| Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | Ghifari Ahmad Lustiansyah |
| Date Deposited: | 10 Aug 2022 06:36 |
| Last Modified: | 10 Aug 2022 06:36 |
| URI: | http://repository.upnvj.ac.id/id/eprint/20338 |
Actions (login required)
 |
View Item |