Skripsi

ANALISIS SENTIMEN TERHADAP ULASAN APLIKASI DANA MENGGUNAKAN WORD2VEC DAN LONG SHORT-TERM MEMORY (LSTM)

---

DANA has become one of the most popular e-wallet applications in Indonesia. This development has elicited various reactions and responses from users in the form of reviews. These reviews can provide important insights for improving the quality of the application's services. This study aims to conduct sentiment analysis on user reviews by utilizing Long Short-Term Memory (LSTM) as the model architecture and Word2Vec as the embedding technique. Word2Vec is used to represent words as numerical vectors, while LSTM understands the context of sentences by processing words sequentially. The best model scenario involves a configuration of 32 LSTM units, dropout 0.2, batch size 128, learning rate 0.001, and 50 epochs. Model evaluation results achieved 92.92% accuracy, 92.91% precision, 92.54% recall, and 92.71% F1-score. These results indicate that the system has the ability to identify user sentiment, making it useful for application development, particularly in improving user satisfaction.

---

Availability

Detail Information

Series Title

-

Call Number

T1955622026

Publisher

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

Collation

xvii, VI-2 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.310 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Analisis sentimen
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment