Skripsi

KLASIFIKASI HATE SPEECH DAN ABUSIVE LANGUAGE PADA TEKS MENGGUNAKAN METODE LONG SHORT-TERM MEMORY (LSTM)

---

Penilaian

---

Social media is an online platform that allows users to share content, interact with other users, create statuses, and also leave comments. Users can freely make comments that contain hate speech and abusive language. One platform that is widely used to make these comments is Twitter. This research aims to classify hate speech and abusive language in text. The method used is Long Short Term Memory (LSTM) and Word2Vec as word embedding. The data used is multilabel class and taken from Kaggle with a total data of 13,169 tweets which are then divided into 80% training data and 20% test data. After manually searching for random hyperparameters 10 times for each hyperparameter, the best results were obtained for the LSTM model with a dropout configuration of 0.2, hidden unit 256, recurrent dropout in the LSTM layer 0.2, epochs 15, and batch size 32. After the research, the average hamming loss value was 0.153.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407000120	T137346	T1373462023	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1373462023

Publisher

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

Collation

xvi, 75 hlm.; Ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.507

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
Program Aplikasi dengan Kegunaan Khusus

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment