Skripsi

PENERAPAN INDOBERT UNTUK ANALISIS SENTIMEN DAN LATENT DIRICHLET ALLOCATION (LDA) UNTUK PEMODELAN TOPIK PADA ULASAN APLIKASI BANK SUMSELBABEL MOBILE

---

Penilaian

---

Mobile banking is one example of how traditional banking services have transformed into digital banking services thanks to advances in digital technology. Bank SumselBabel Mobile application is the main focus of research to understand user perception. This research aims to analyze sentiment using the IndoBERT and BERT methods as a performance comparison, as well as identify the main topics in the reviews using Latent Dirichlet Allocation (LDA). The review data was collected on October 30, 2024 with a total of 2632 reviews. IndoBERT has superior performance compared to BERT in analyzing sentiment, with an F1-score of 93% versus 88%. This shows IndoBERT's ability to understand the nuances of Indonesian better than BERT. Furthermore, topic modeling using LDA on each sentiment produces a coherence value of 0.4559 for negative sentiment, 0.4058 for neutral, and 0.4114 for positive sentiment.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407007133	T163162	T1631622024	Central Library (REFERENS)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1631622024

Publisher

Indralaya : Prodi Sistem Informasi, Fakultas Ilmu Komputer Universitas Sriwijaya., 2024

Collation

xvi, 67 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

003.010 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Sistem Informasi
Identifikasi Sistem

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment