Dinda Aulia Setianingsih, . (2024) KLASIFIKASI SENTIMEN ULASAN PENGGUNA MENGGUNAKAN METODE SUPPORT VECTOR MACHINE PADA APLIKASI BIBIT DAN BAREKSA. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (16kB) |
|
Text
AWAL.pdf Download (331kB) |
|
Text
BAB 1.pdf Download (103kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (170kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (242kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (71kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (148kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (19kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (282kB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (538kB) |
Abstract
The rapid advancement of technology has impacted various industries, including the financial sector. Purchasing mutual funds, stocks, and other investment assets, which were previously done conventionally, can now be easily accomplished through applications on smartphones. Applications such as Bibit and Bareksa provide services for purchasing mutual funds and other investment products. The convenience offered by these investment applications has attracted the interest of various demographics, including the younger generation. Bibit and Bareksa applications have received considerable criticism and feedback from users. This research aims to delve deeper into user reviews of these applications through sentiment analysis and to develop a simple website using the Flask framework that can classify user input reviews. The Support vector machine algorithm with a linear kernel is employed to classify positive and negative sentiments, with and without chi-square feature selection, to achieve the best accuracy. In the Bibit application, using chi-square yielded an accuracy of 92%, precision of 94%, recall of 89%, and f1-score of 91%. Without chi-square, the accuracy was 91%, precision was 94%, recall was 88%, and f1-score was 91%. For the Bareksa application, using chi-square resulted in an accuracy of 86%, precision of 85%, recall of 87%, and f1-score of 86%. Without chi-square, the accuracy was 84%, precision was 83%, recall was 85%, and f1-score was 84%. The classification results indicate that the utilization of chi-square feature selection in this study leads to improved accuracy, with an increase of 1% to 2%.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2010512035] [Pembimbing 1: Ika Nurlaili Isnainiyah] [Pembimbing 2: Nindy Irzavika] [Penguji 1: Nur Hafifah Matondang] [Penguji 2: Sarika] |
| Uncontrolled Keywords: | Sentiment Analysis, Support Vector Machine, Chi-square, Bibit, Bareksa |
| Subjects: | 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 Sistem Informasi (S1) |
| Depositing User: | DINDA AULIA SETIANINGSIH |
| Date Deposited: | 12 Sep 2024 03:20 |
| Last Modified: | 12 Sep 2024 03:20 |
| URI: | http://repository.upnvj.ac.id/id/eprint/30757 |
Actions (login required)
 |
View Item |