Skripsi

KLASIFIKASI SENTIMEN REVIEW APLIKASI EDUTECH ZENIUS DENGAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK

---

Penilaian

---

Zenius is one of the rapidly growing edutech applications in Indonesia. In the edutech industry, understanding and promptly responding to user reviews is crucial to enhance the quality of the application's services, enabling Zenius to remain competitive against other competitors. In order to achieve this, sentiment classification is used by classifying user reviews into positive, negative, or neutral categories using a classification algorithm. In this research, the Convolutional Neural Network (CNN) algorithm is used as the classification method, while Word2Vec is used as the word embedding technique. The dataset used in this research consists of 1,587 user reviews of the Zenius application obtained from the Google Play Store website. The results of the research demonstrate the best CNN model using a configuration of a learning rate=〖10〗^(-3), a batch size=16 and 3 convolution layers with an accuracy value of 84.28%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307002536	T114370	T1143702023	Central Library (Referens)	Available

Detail Information

Series Title

-

Call Number

T1143702023

Publisher

Indralaya : Jurusan Teknik Informatika Fakultas Ilmu Komputer Universtas Sriwijaya., 2023

Collation

xx, 115 hlm.; Ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.507

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Aplikasi
Jurusan Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

FIRA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment