Skripsi

ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI GOJEK MENGGUNAKAN LONG SHORT TERM MEMORY (LSTM)

---

his study aims to analyze user sentiment toward the Gojek application using the Long Short-Term Memory (LSTM) method. Review data was obtained through scraping the Gojek application service, resulting in a dataset that was then classified into positive and negative sentiment categories. The data underwent class balancing using the undersampling technique, followed by a pre-processing stage that included case folding, text cleaning, normalization, stopword removal, stemming, tokenization, and padding before being used in model training. This study applied five hyperparameter testing scenarios to find the best configuration for sentiment classification. The evaluation results show that the first scenario with a configuration of 10 epochs, a batch size of 32, and 64 LSTM units provides the most optimal performance with an accuracy rate of 93.07%. These findings prove that the LSTM algorithm is very effective in recognizing the context of Indonesian-language online transportation service reviews and can be an evaluation tool for service providers to automatically improve the quality of the user experience.

---

Availability

Detail Information

Series Title

-

Call Number

T1957132026

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xiv, 19 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.350 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Analisis sentimen
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

TUTI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment