Please use this identifier to cite or link to this item:
https://repositori.uma.ac.id/handle/123456789/29596| Title: | Klasifikasi Ujaran Kebencian di Twitter Menggunakan Algoritma Radial Basis Function Network (RBFN) |
| Other Titles: | Classification of Hate Speech on Twitter Using Radial Basis Function Network (RBFN) Algorithm |
| Authors: | Sitompul, Dani Gunawan |
| metadata.dc.contributor.advisor: | Sembiringq, Arnes |
| Keywords: | Ujaran Kebencian;Twitter;Text Preprocessing;Radial Basis Function Network (RBFN);TF-IDF;Klasifikasi;Hate Speech;Classification |
| Issue Date: | Jun-2025 |
| Publisher: | Universitas Medan Area |
| Series/Report no.: | NPM;188160010 |
| Abstract: | Penelitian ini bertujuan untuk mengklasifikasikan ujaran kebencian di media sosial Twitter menggunakan algoritma Radial Basis Function Network (RBFN). Latar belakang penelitian ini didasarkan pada maraknya penyebaran ujaran kebencian di media sosial yang dapat memicu konflik sosial dan mengganggu keharmonisan masyarakat. Data penelitian diperoleh secara langsung dari Twitter melalui API V2 dengan kata kunci “ujaran kebencian”, berjumlah 600 tweet berbahasa Indonesia. Tahapan penelitian meliputi text preprocessing yang terdiri dari case folding, tokenization, stopwords removal, stemming, serta pembobotan kata menggunakan metode Term Frequency–Inverse Document Frequency (TF-IDF). Model RBFN digunakan sebagai metode klasifikasi untuk membedakan antara tweet yang mengandung ujaran kebencian (hate speech) dan yang tidak (non-hate speech). Evaluasi dilakukan menggunakan confusion matrix dengan metrik akurasi, presisi, dan recall pada tiga skenario pembagian data, yaitu 70:30, 80:20, dan 90:10. Hasil pengujian menunjukkan bahwa model memperoleh akurasi tertinggi sebesar 87,7% pada pembagian data 70% untuk pelatihan dan 30% untuk pengujian. Hasil ini menunjukkan bahwa algoritma RBFN mampu memberikan performa yang baik dalam mengklasifikasikan ujaran kebencian di Twitter. Penelitian ini diharapkan dapat menjadi acuan dalam pengembangan sistem deteksi ujaran kebencian secara otomatis untuk menciptakan lingkungan media sosial yang lebih sehat dan aman. This research aims to classify hate speech on the social media platform Twitter using the Radial Basis Function Network (RBFN) algorithm. The background of this study stems from the widespread dissemination of hate speech on social media, which can trigger social conflicts and disrupt public harmony. The dataset was collected directly from Twitter through API V2 using the keyword “ujaran kebencian,” consisting of 600 Indonesian-language tweets. The research stages include text preprocessing, which involves case folding, tokenization, stopwords removal, stemming, and word weighting using the Term Frequency–Inverse Document Frequency (TF-IDF) method. The RBFN model was applied to classify tweets into hate speech and non-hate speech categories. Model evaluation was conducted using a confusion matrix with accuracy, precision, and recall metrics across three data-splitting scenarios: 70:30, 80:20, and 90:10. The results show that the model achieved the highest accuracy of 87.7% under the 70:30 data-splitting configuration. These findings indicate that the RBFN algorithm performs effectively in classifying hate speech on Twitter. This study is expected to serve as a reference for developing automated hate speech detection systems to promote a safer and more positive online environment. |
| Description: | 42 Halaman |
| URI: | https://repositori.uma.ac.id/handle/123456789/29596 |
| Appears in Collections: | SP - Informatic Engineering |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 188160010 - Dani Gunawan Sitompul - Fulltext.pdf | Cover, Abstract, Chapter I, II, III, V, Bibliography | 1.55 MB | Adobe PDF | View/Open |
| 188160010 - Dani Gunawan Sitompul - Chapter IV.pdf Restricted Access | Chapter IV | 554.04 kB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.