Skripsi

KLASIFIKASI EMOSI PADA KALIMAT DI TWITTER MENGGUNAKAN ALGORITMA LONG SHORT-TERM MEMORY

---

Penilaian

---

Emotions have an important role in human life, especially in social interactions on social media platforms such as Twitter. The classification of emotions in an important sentence plays a role in analyzing public opinion and can help in decision making. The Long Short-Term Memory (LSTM) algorithm is a refinement of the Recurrent Neural Network (RNN) algorithm which is able to manage sequential data, overcome dependencies between words in a sentence, and control information in memory such as remembering important information and deleting irrelevant information. Therefore, LSTM is an effective method to use in the process of classifying emotions in a sentence. The data used in this research amounted to 1000 data where there were 5 emotion classes with equal numbers. The model creation process was carried out using several tests by tuning the learning rate and batch size parameters. The research results show that the learning rate = 0.001 and batch size = 16 produce the best performance with accuracy and recall values of 77% and precision and f1-score values of 76.8%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407000447	T137933	T1379332023	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1379332023

Publisher

Inderalaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2023

Collation

xivii, 72 hlm.; Ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.07

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Pemrosesan data
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment