Dyah Pramesti, . (2025) ANALISIS DATA ULASAN PENGGUNA TERHADAP FITUR UTAMA APLIKASI MOBILE BANKING BANK XYZ MENGGUNAKAN ALGORITMA NAIVE BAYES. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (172kB) |
|
Text
AWAL.pdf Download (742kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (261kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (440kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (431kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (6MB) |
|
Text
BAB 5.pdf Download (224kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (199kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (116kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (6MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (18MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (4MB) |
Abstract
Digital banking services through mobile banking applications are expected to provide optimal performance and a satisfying user experience. However, various user complaints are still found, particularly related to application stability, technical issues, and transaction delays. This study aims to analyze user sentiment toward a mobile banking application using the Naive Bayes algorithm, with the goal of providing an overview of user perceptions and recommendations for service improvement. The research data were collected through questionnaires distributed to active users, resulting in 443 user reviews covering key features such as transfers, payments, QRIS, top-up, and overall performance. The data were processed through several stages, including preprocessing, sentiment labeling, and word weighting using the TF-IDF method. Sentiment classification modeling was performed using the Naive Bayes algorithm and compared with Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) as benchmarking algorithms. Testing was conducted using the 5-Fold Cross Validation method with an 80% training and 20% testing data split in each fold. The evaluation results show that the Naive Bayes algorithm achieved an average precision of 82%, recall of 81%, and F1-score of 81%, indicating that the algorithm is feasible and fairly effective for classifying user sentiment reviews. The research results were implemented into a web-based dashboard as a means of data visualization.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No. Panggil: 2110512011] [Pembimbing 1: Tjahjanto] [Pembimbing 2: Bambang Triwahyono] [Penguji 1: Bambang Saras Yulistiawan] [Penguji 2: Novi Trisman Hadi] |
| Uncontrolled Keywords: | Naive Bayes Algorithm, Sentiment Analysis, Text Classification, User Reviews, Mobile Banking |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Sistem Informasi (S1) |
| Depositing User: | DYAH PRAMESTI |
| Date Deposited: | 25 Aug 2025 04:04 |
| Last Modified: | 25 Aug 2025 04:04 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37494 |
Actions (login required)
 |
View Item |