Skripsi

KLASIFIKASI KOMENTAR BULLYING PADA YOUTUBE DENGAN METODE LONG SHORT-TERM MEMORY

---

Penilaian

---

YouTube is one of the most popular online video-watching platforms on the internet. Bullying on social media, including on the YouTube platform, is a serious issue that can have negative impacts on mental health and individual well-being. This research aims to address this problem by developing a comment classification model using the Long Short-Term Memory method to identify bullying comments on YouTube. The data used were obtained from comments on several YouTube videos, consisting of 400 bullying comments and 400 non-bullying comments. Testing was conducted using 6 experimental scenarios, and the best test results were achieved with the following hyperparameters: a dropout layer value of 0, 128 neurons in the LSTM layer with an LSTM dropout value of 0, a learning rate of 0.001, a batch size of 8, and an epoch of 10. The results yielded an accuracy of 96.84%, precision of 96.84%, recall of 96.84%, and an f1-score of 96.83%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407004186	T150430	T1504302024	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1504302024

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2024

Collation

xv, V-18 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
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