Analisis Sentimen Hate Speech Pada Portal Berita Online Menggunakan Support Vector Machine (SVM)

Aniq Noviciatie Ulfah, Aniq Noviciatie Ulfah and M. Khairul Anam, M. Khairul Anam (2020) Analisis Sentimen Hate Speech Pada Portal Berita Online Menggunakan Support Vector Machine (SVM). JATISI (Jurnal Teknik Informatika dan Sistem Informasi), 7 (1). pp. 1-10. ISSN ISSN 2407, E-ISSN 2503-2933

Text Analisis Sentimen Hate Speech Pada Portal Berita Online.pdf - Other Download (175kB)

Abstract

Hate speech is a form of crime in which the violator threatened with punishment by ITE law. But now netizens in Indonesia still use many of the words of Hate Speech in commenting on news in the online media. The impact of this situation is many netizens currently being sued by the police for those who feel disadvantaged. It happens because of the lack of information from netizens about hate speech. The research to be conducted is related to the detection of words that contain Hate Speech in the online news port. The approach used to detect Hate Speech words uses Neural Language Processing using the Support Vector Machine (SVM) method. Several trial scenarios were carried out to measure the level of accuracy so that the level of accuracy was better. Comments on this study obtain on the most popular online news portal in Indonesia. SVM algorithm applied in analyzing comments related to political issues that contain Hate Speech with an accuracy value that can be as big as 53. 88% and Recall value is 49.69%, Precision is 48.77%, Classification error is 46.12%, and feature is 49.23%. With this research to be conducted, it can become a news portal reference for implementing a filtering system to reduce the possibility of Hate Speech cases.

Item Type:	Article
Uncontrolled Keywords:	Portal berita, Hate Speech, Support Vector Machine
Subjects:	T Technology > T Technology (General)
Divisions:	Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science
Depositing User:	Mrs Ni Made Yunia Dwi Savitri
Date Deposited:	17 Nov 2022 01:34
Last Modified:	17 Nov 2022 01:34
URI:	http://eprints.triatmamulya.ac.id/id/eprint/1790

Actions (login required)

View Item