Skripsi

KLASIFIKASI TEKS PEMIKIRAN BUNUH DIRI MENGGUNAKAN BIDIRECTIONAL LONG SHORT TERM MEMORY

---

Penilaian

---

Social media has emerged as a new platform for individuals to express their thoughts and emotions through various posts. Among these expressions, suicidal ideation is occasionally found, which requires immediate responses. This study focuses on the text classification that containing suicidal ideation. The method used in this research is the Bidirectional Long Short-Term Memory (Bi-LSTM) as the model due to its superior capability in capturing and understanding contextual information, utilizing Word2Vec for word embedding representation. The dataset consists of 15.477 entries, which were divided into 80% for training and 20% for testing. Additionally, 10% of the training data was allocated for validation purposes. After conducting 12 hyperparameter configuration trials using the brute-force method, the best configuration was achieved with a learning rate of 0.001, a batch size of 64, and 10 epochs. The model attained a recall of 92%, and an accuracy of 93%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507005326	T182378	T1823782025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1823782025

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xvii, 64 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

005.307

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
Bidirectional Long Short Term Memory

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment