Pendeteksian Hate Speech Pada Sosial Media Indonesia Dengan Algoritma Support Vector Machine (Svm) Dan Decision Tree

Kusuma, Febrian Andy and -, Endang Wahyu Pamungkas, S.Kom., M.Kom (2023) Pendeteksian Hate Speech Pada Sosial Media Indonesia Dengan Algoritma Support Vector Machine (Svm) Dan Decision Tree. Skripsi thesis, Universitas Muhammadiyah Surakarta.

	PDF (Naskah Publikasi) Naskah Publikasi_Febrian Andy Kusuma_L200190137.pdf (1)2.pdf Download (384kB)
	PDF (Surat Pernyataan Publikasi) Doc1.pdf Restricted to Repository staff only Download (445kB) | Request a copy

Abstract

Hate Speech is any speech, gesture, behavior, writing, or display that can trigger violence or harmful actions because belittling and intimidating certain individuals or groups can encourage or trigger hatred. Hate speech can be in the form of words, pictures, and other forms of expression. Hate Speech causes hatred for a particular group or individual. Hate Speech is usually carried out by individuals who have a dislike for a group with the aim of inciting others to hate the group. The comment column on Twitter needs restrictions and awareness from the public about the dangers of hate speech which can lead to prolonged conflict. This study aims to determine the accuracy of the detection of foul language from the application of the Support Vector Machine (SVM) and Decision Tree algorithms. This method is applied to the Indonesian Twitter dataset with a total of 13,169 data lines. This research resulted in the detection of Hate Speech in Indonesian language tweets with the highest performance in the SVM model with a precision of 84%, Recall of 89%, Accuracy of 83% and F1-Score of 86%.

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	decision tree, support vector machine, detection hate speech
Subjects:	T Technology > TZ Technical Information > Software. Aplication
Divisions:	Fakultas Ilmu Komunikasi dan Informatika > Teknik Informatika
Depositing User:	FEBRIAN ANDY KUSUMA
Date Deposited:	11 May 2023 01:48
Last Modified:	11 May 2023 01:48
URI:	http://eprints.ums.ac.id/id/eprint/111722

Actions (login required)

View Item