Dewa, Bhagas Satrya (2026) Klasifikasi Multi-Label Faktor ECM IS Continuance Intention pada Ulasan Aplikasi Blu By Bca Digital Menggunakan IndoBERT dan Ner. Undergraduate thesis, UPN Veteran Jawa Timur.
|
Text (Cover)
Cover.pdf Download (1MB) | Preview |
|
|
Text (Bab 1)
Bab 1.pdf Download (440kB) | Preview |
|
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Bab 2)
Bab 2.pdf Restricted to Repository staff only until 25 May 2028. Download (670kB) |
|
|
Text (Bab 3)
Bab 3.pdf Restricted to Repository staff only until 25 May 2028. Download (702kB) |
|
|
Text (Bab 4)
Bab 4.pdf Restricted to Repository staff only until 25 May 2028. Download (6MB) |
|
|
Text (Bab 5)
Bab 5.pdf Download (290kB) | Preview |
|
|
Text (Daftar Pustaka)
Daftar Pustaka.pdf Download (305kB) | Preview |
|
|
Text (Lampiran)
Lampiran.pdf Restricted to Repository staff only Download (829kB) |
Abstract
The rapid growth of digital banking in Indonesia has intensified competition in retaining active users. Blu by BCA Digital, despite achieving a brand awareness rate of 85%, retained only 26% of active users within the past month, while merely 38% of respondents reported ever having used the application. This gap is further evidenced by the prevalence of negative reviews on Google Play Store, reflecting user dissatisfaction with application performance, login processes, and transaction speed, indicating substantial challenges in sustaining user retention. This study aims to build a multi-label intent classification model using IndoBERT and Named Entity Recognition (NER) to identify the determinants of IS Continuance Intention, as well as to develop a web-based dashboard for result visualization. User reviews were collected from Google Play Store and Apple Store, then labeled based on four Expectation-Confirmation Model (ECM) factors, namely Confirmation, Perceived Usefulness, E-satisfaction, and Perceived Security, along with six NER entities. The best intent classification model achieved an F1-Score of 0.797 and a Hamming Loss of 0.131, while the best NER model reached an F1-Score of 0.812. The developed web-based dashboard integrates both models, supports single-text and CSV file input, and presents prediction results informatively.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | Q Science > QA Mathematics Q Science > QA Mathematics > QA76.6 Computer Programming T Technology > T Technology (General) T Technology > T Technology (General) > T58.6-58.62 Management Information Systems |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Information Systems | ||||||||||||
| Depositing User: | Bhagas Satrya Dewa | ||||||||||||
| Date Deposited: | 25 May 2026 08:41 | ||||||||||||
| Last Modified: | 25 May 2026 08:41 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/52288 |
Actions (login required)
 |
View Item |