Skripsi

ANALISIS SENTIMEN ULASAN APLIKASI MOBILE BANKING LIVIN’ BY MANDIRI PADA GOOGLE PLAY STORE MENGGUNAKAN METODE LONG SHORT-TERM MEMORY (LSTM)

---

Penilaian

---

Mobile banking apps are growing in popularity in Indonesia, one of which is Livin' by Mandiri, which ranks third in highest usage according to GoodStats 2022 data. Understanding app user reviews can influence the level of satisfaction with the app. This research aims to fill the gap by analyzing review sentiment using the Long Short-Term Memory (LSTM) method and FastText word embedding. LSTM was chosen for its ability to understand text context, while FastText is used to represent words in the form of numerical vectors, including handling new or rarely used words. The best model, using a configuration of 128 LSTM units, dropout 0.3, dense layer 32, learning rate 0.001, batch size 128, and 20 epochs, achieved 85% accuracy,77% precision, 70% recall, and 71% F1-score. These results show that the system is able to identify review sentiment well,support application development, and improve user experience.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507001494	T168783	T1687832025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1687832025

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xv, 126 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

005.507

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Aplikasi Mobile Banking

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment