Pendeteksian Ujaran Seksisme Pada Platform X Dengan Algoritma Machine Learning Tradisional

Fattah, Hasyim Al and , Endang Wahyu Pamungkas, S.Kom, M.Kom. (2024) Pendeteksian Ujaran Seksisme Pada Platform X Dengan Algoritma Machine Learning Tradisional. Skripsi thesis, Universitas Muhammadiyah Surakarta.

	PDF (Naskah Publikasi) L200200109_Hasyim Al Fattah.pdf Download (670kB)
	PDF (Surat Pernyataan Publikasi) Doc1hasyim.pdf Restricted to Repository staff only Download (293kB) | Request a copy

Abstract

This study explores the impact of the internet and social media in Indonesia, with a focus on Twitter as a popular platform, specifically regarding sexist speech against Nadin Amizah. This study uses supervised learning methods with Support Vector Machine (SVM) and Naïve Bayes algorithms to analyze Indonesian Twitter data. The data used amounted to 1622 tweets, collected between September 25 and October 11, 2023. After preprocessing, the amount of data used for sentiment analysis was 1474 tweets. The analysis results show that 82.56% (1217 tweets) have positive or non-sexist labels and 17.44% (257 tweets) have negative labels. The SVM algorithm achieved an accuracy of 80.36%, while the Naïve Bayes algorithm achieved an accuracy of 68.62%. The main objective of this research is to understand the impact of sexist speech and perform prediction and sentiment analysis on the topic. The results of this analysis provide a deeper understanding of the use of machine learning techniques in the context of sexism speech detection, and provide a basis for sustainable decisions in addressing the problem of sexism speech on social media.

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	Sexism, Twitter, SVM, Naïve Bayes.
Subjects:	T Technology > TZ Technical Information
Divisions:	Fakultas Ilmu Komunikasi dan Informatika > Teknik Informatika
Depositing User:	HASYIM AL FATTAH
Date Deposited:	06 Aug 2024 06:48
Last Modified:	06 Aug 2024 06:48
URI:	http://eprints.ums.ac.id/id/eprint/125966

Actions (login required)

View Item