Text

KLASIFIKASI EMOSI PADA TEKS TWITTER MENGGUNAKAN LONG SHORT-TERM MEMORY (LSTM)

---

Penilaian

---

Emotions have an important role in everyday life because the expression of emotions can help to provide information about the status of an individual's interaction with other individuals and their environment. There are six emotions, such as: Happy, sad, scared, disgusted, angry, and surprised. One of the platform that many people choose to express their emo tions is through social media. This study aims to build a software to classify emotions on twitter text using Long Short�Term Memory and determine its performance. Data used in this study were collected through crawling on Twitter using rapidminer to get a total of 24,000 tweets. The data that have been collected then divided into training data and testing data, then the data went through the pre-processing stage before being entered into the LSTM layer. The data were then classified using the LSTM method and trained using 10 fold K-Fold Cross Validation. Based on the results of the classification, it is known that the greatest accuracy is in the K -Fold 5 with the accuracy score of 88.30% and the loss value of 0.022.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207002263	T74293	T742932022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T742932022

Publisher

Inderalaya : Jurusan Teknik Informatika, Fakultas Pertanian., 2022

Collation

xvii, 79 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.754 07

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Teknik Informatika
Situs Jejaring Sosial

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment