Skripsi

OTOMATISASI ULASAN PENGGUNA: DETEKSI KELUHAN ACTIONABLE PADA GOJEK DI PLAY STORE MENGGUNAKAN METODE LSTM

---

This study aims to develop an automatic complaint detection system for Gojek application reviews using Long Short-Term Memory (LSTM). The dataset used in this research consists of 225,002 user reviews obtained from the Play Store. The objective is to build a system capable of classifying user reviews into two labels. The processing was carried out using three different data-split ratios to ensure that the developed system is stable and effective. The accuracy results from all three ratios exceeded 90%, demonstrating that the system is capable of detecting complaints successfully. To facilitate the monitoring of classification results, a confusion matrix and a pre-built dashboard were used to visualize the LSTM-based model. This system is expected to assist the company in identifying user complaints and finding solutions to improve services, thereby enhancing user comfort.

---

Availability

Detail Information

Series Title

-

Call Number

T1894892025

Publisher

Indralaya : Prodi Sistem Informasi, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xvii, 97 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

006.350 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Sistem Informasi
Pembelajaran Mesin--Deteksi Ulasan Pengguna

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment