Hate Speech Detection On Social Media Content In Javanese Language With Naive Bayes Algorithm

Yati, Juniar Darma and , Endang Wahyu Pamungkas, S.Kom, M.Kom. Hate Speech Detection On Social Media Content In Javanese Language With Naive Bayes Algorithm. Skripsi thesis, Universitas Muhammadiyah Surakarta.

	PDF (Naskah Publikasi) NaskahPublikasi.pdf Download (239kB)
	PDF (Surat Pernyataan Publikasi) SURAT PUBLIKASI.pdf Restricted to Repository staff only Download (324kB)

Abstract

Social media allows users to reach out and facilitate positive and constructive conversations between users around the world. Twitter is one of the social media that enables its users to communicate by writing and publishing opinions freely. These opinions can contain congratulations, happiness, praise, and hatred, usually written in commonly used and very diverse languages, including Javanese. The authors researched a system designed to test the performance of each Naïve Bayes algorithm model, namely Gaussian Naïve Bayes, Multinomial Naïve Bayes, and Bernoulli Naïve Bayes in detecting and classifying Javanese hate speech on Twitter using the Python programming language. The study used data from a Twitter dataset of 3477 Javanese tweets. The data will split into two parts with a ratio of 80%-20%, with the results of 2781 training data and 696 test data. Classification and evaluation resulted in 98% accuracy, 100% precision, 54% recall, and 70% F1-score using the Naïve Bayes Multinomial model and through preprocessing.

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	hate speech, javanese, naïve bayes, twitter.
Subjects:	T Technology > TZ Technical Information
Divisions:	Fakultas Ilmu Komunikasi dan Informatika > Teknik Informatika
Depositing User:	JUNIAR DARMA YATI
Date Deposited:	23 May 2023 02:52
Last Modified:	23 May 2023 02:52
URI:	http://eprints.ums.ac.id/id/eprint/112433

Actions (login required)

View Item