KLASIFIKASI TEKS PEMIKIRAN BUNUH DIRI MENGGUNAKAN BIDIRECTIONAL LONG SHORT TERM MEMORY

YASARA, SALMA and Yusliani, Novi and Rodiah, Desty (2025) KLASIFIKASI TEKS PEMIKIRAN BUNUH DIRI MENGGUNAKAN BIDIRECTIONAL LONG SHORT TERM MEMORY. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_55201_09021282126072_cover.jpg] Image
RAMA_55201_09021282126072_cover.jpg - Cover Image
Available under License Creative Commons Public Domain Dedication.

Download (144kB)
[thumbnail of RAMA_55201_09021282126072.pdf] Text
RAMA_55201_09021282126072.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (5MB) | Request a copy
[thumbnail of RAMA_55201_09021282126072_TURNITIN.pdf] Text
RAMA_55201_09021282126072_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (9MB) | Request a copy
[thumbnail of RAMA_55201_09021282126072_0008118205_0021128905_01_front_ref.pdf] Text
RAMA_55201_09021282126072_0008118205_0021128905_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (831kB)
[thumbnail of RAMA_55201_09021282126072_0008118205_0021128905_02.pdf] Text
RAMA_55201_09021282126072_0008118205_0021128905_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (712kB) | Request a copy
[thumbnail of RAMA_55201_09021282126072_0008118205_0021128905_03.pdf] Text
RAMA_55201_09021282126072_0008118205_0021128905_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (433kB) | Request a copy
[thumbnail of RAMA_55201_09021282126072_0008118205_0021128905_04.pdf] Text
RAMA_55201_09021282126072_0008118205_0021128905_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_55201_09021282126072_0008118205_0021128905_05.pdf] Text
RAMA_55201_09021282126072_0008118205_0021128905_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_55201_09021282126072_0008118205_0021128905_06.pdf] Text
RAMA_55201_09021282126072_0008118205_0021128905_06.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (200kB) | Request a copy
[thumbnail of RAMA_55201_09021282126072_0008118205_0021128905_07_ref.pdf] Text
RAMA_55201_09021282126072_0008118205_0021128905_07_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (159kB) | Request a copy
[thumbnail of RAMA_55201_09021282126072_0008118205_0021128905_08_lamp.pdf] Text
RAMA_55201_09021282126072_0008118205_0021128905_08_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (198kB) | Request a copy

Abstract

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%.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Klasifikasi Teks, Word2Vec, Bidirectional Long Short Term Memory, Pemikiran Bunuh Diri
Subjects: T Technology > T Technology (General) > T1-995 Technology (General)
Divisions: 09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User: Salma Yasara
Date Deposited: 06 Aug 2025 01:48
Last Modified: 06 Aug 2025 01:48
URI: http://repository.unsri.ac.id/id/eprint/182378

Actions (login required)

View Item View Item