Aplikasi Pendeteksi Berita Palsu Bahasa Indonesia Menggunakan Framework Flask dan Streamlit serta Algoritma Machine Learning

Amal, Ikhlasul and , Endang Wahyu Pamungkas, S.Kom., M.Kom., Ph.D. (2023) Aplikasi Pendeteksi Berita Palsu Bahasa Indonesia Menggunakan Framework Flask dan Streamlit serta Algoritma Machine Learning. Skripsi thesis, Universitas Muhammadiyah Surakarta.

	PDF (Naskah Publikasi) Naskah Publikasi_Ikhlasul Amal.pdf Download (616kB)
	PDF (Surat Pernyataan Publikasi) Surat Pernyataan Publikasi_Ikhlasul Amal.pdf Restricted to Repository staff only Download (132kB)

Abstract

Technological advancements and the widespread use of the internet have enabled society to access information rapidly. However, this has also led to an increase in the dissemination of fake news or hoaxes. This research aims to examine the effectiveness of four classification algorithms (Naive Bayes, Decision Tree, Logistic Regression, and Random Forest) in detecting fake news in the Indonesian language. Additionally, the study implements these classification algorithms into two frameworks, namely Flask and Streamlit, to develop an application for detecting fake news in the Indonesian language. The dataset used for this research consists of 600 news articles labeled as 'Valid' and 'Hoax.' The four machine learning algorithms are evaluated using automated testing to measure their performance using accuracy, precision, recall, and F1-score metrics. The results of the automated testing reveal that Random Forest attains the highest accuracy (74%), with a balanced precision and recall for both 'Valid' and 'Hoax' labels, while Naive Bayes records the lowest accuracy (64%). Furthermore, manual testing on 20 news articles indicates that Random Forest and Decision Tree provide more accurate results compared to Naive Bayes and Logistic Regression. The implementation of the classification algorithms using Flask and Streamlit frameworks for the fake news detection application is successfully accomplished. The outcomes of this research are expected to contribute to reducing the negative impact caused by fake news and increasing public awareness regarding the importance of verifying information before disseminating it.

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	algoritma machine learning, Flask, berita palsu, Streamlit
Subjects:	Q Science > QA Mathematics > QA76 Computer software T Technology > TZ Technical Information > Software. Aplication
Divisions:	Fakultas Ilmu Komunikasi dan Informatika > Teknik Informatika
Depositing User:	IKHLASUL AMAL
Date Deposited:	19 Aug 2023 04:00
Last Modified:	19 Aug 2023 04:00
URI:	http://eprints.ums.ac.id/id/eprint/116531

Actions (login required)

View Item