Skripsi

KLASIFIKASI UJARAN KEBENCIAN BAHASA INDONESIA MENGGUNAKAN INDOBERT DAN CONVOLUTIONAL NEURAL NETWORK (CNN)

---

The increasing spread of hate speech on social media, particularly on Twitter (X), poses challenges for manual content moderation, which tends to be ineffective. This condition highlights the need for an automated classification system capable of accurately detecting hate speech. This study aims to develop a hate speech classification model using approach combining IndoBERT and Convolutional Neural Network (CNN), and to evaluate its performance based on accuracy, precision, recall, and F1-score metrics. The dataset used in this study is the Indonesian Abusive and Hate Speech Twitter Text dataset consisting of 13,169 data. Text representations were generated using IndoBERT as a contextual embedding, and further processed by CNN to extract local features and perform binary classification. The best result was achieved using a configuration with kernel size 7, 128 filters, and a dropout rate of 0.5, resulting in an accuracy of 86.97%, precision of 86.96%, recall of 86.97%, and F1-score of 86.91%, indicating that the model is capable of classifying hate speech with very good performance.

---

Availability

Detail Information

Series Title

-

Call Number

T1988762026

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xvii, 147 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

006.320 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
Indobert

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment