Skripsi

KLASIFIKASI EMOSI PADA TWITTER MENGGUNAKAN BIDIRECTIONAL LONG SHORT TERM MEMORY

---

Penilaian

---

Twitter is one of the social media platforms where users can share messages. These messages often contain emotions. The conveyed emotions in these tweets can be recognized through an emotion classification process. However, the text data in tweets is often unstructured, so the appropriate method needs to be applied for emotion classification. The method used in this research involves the utilization of Deep Learning algorithm, specifically Bidirectional Long Short Term Memory (Bi-LSTM), which is an extension of the Long Short Term Memory (LSTM) method for emotion classification. The emotion classification process in this research utilizes 3185 data, which is then divided into 80% training data and 20% testing data. Additionally, the use of Word2Vec word embedding is implemented to maximize the results. After tuning the hyperparameters using random search, the best final result for the Bi-LSTM model is obtained with a dropout layer of 0.2, hidden units of 128, dropout in the Bi-LSTM layer of 0.3, recurrent dropout of 0.4, 10 epochs, and a batch size of 32. The final evaluation results reach an accuracy of 78% with macro precision, macro recall, and macro F-Measure averaging at 79%, 78%, and 78% respectively. Similarly, the weighted precision, weighted recall, and weighted F-Measure reach 79%, 78%, and 78% respectively, which is considered good for analyzing emotions in Twitter texts.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307003713	T115161	T1151612023	Central Library (REFERENS)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1151612023

Publisher

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

Collation

xiv, 89 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, Sosial Media

Specific Detail Info

-

Statement of Responsibility

ANUG

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment