Article Per Year (5 Year)
p-Index From 2019 - 2024
0.61
P-Index
This Author published in this journals
All Journal Systematics
Fakhri Muhammad
Universitas Singaperbangsa Karawang
Computer Science & IT Library & Information Science

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Analysis of the Relationship between Public Sentiment on Social Media and Indonesian Covid-19 Dynamics: Analisis Hubungan Sentimen Publik di Media Sosial dengan Dinamika Covid-19 Indonesia Nana Mulyana Maghfur; Fakhri Muhammad; Apriade Voutama
SYSTEMATICS Vol 3 No 3 (2021): December 2021
Publisher : Universitas Singaperbangsa Karawang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35706/sys.v3i3.6075

Abstract

The bad side of the open access nature of social media is that it frees anyone to have an opinion as they please and is often accompanied by other agendas such as spreading panic, false information, fake news, hate speech and even distorting public opinion. This condition can be fatal in the pandemic era where public opinion can worsen the pandemic situation. Therefore, it is important to know whether it is true that changes in public sentiment in response to news on social media can affect the dynamics of the spread of COVID-19. We use sentiment analysis using machine learning methods to extract daily sentiment data and test its correlation with daily Covid-19 case data in Indonesia. The results of the associative hypothesis test with a Pearson correlation value of 0.151 show that public sentiment on social media towards the news of the COVID-19 variant is positively correlated with the dynamics of the daily Covid-19 cases. Therefore, the author invites all social media users, including the author himself, to be more vigilant and careful in giving opinions and accepting other people's opinions on social media.
Sentiment Analysis Dataset on COVID-19 Variant News: Kumpulan Data Analisis Sentimen pada Berita Varian COVID-19 Fakhri Muhammad; Nana Mulyana Maghfur; Apriade Voutama
SYSTEMATICS Vol 4 No 1 (2022): April 2022
Publisher : Universitas Singaperbangsa Karawang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35706/sys.v4i1.6347

Abstract

The development of technology at this time is getting faster and faster, this is indicated by the number of emerging social media such as Facebook, Instagram, Twitter. Twitter is used as a forum for users to discuss, express opinions, and share stories between users, because many people today often have opinions about the COVID-19 outbreak, plus there are new variants that make people express various types of opinions, both good and bad. good and so on. Therefore, an effort was made to research the covid variant to see labeling sentiment, which in essence is a text mining process that aims to extract sentiment from text using regular expressions so that labels are obtained for each text in the dataset, so a dataset is formed that can be used for further research. The process includes data collection including (scrapping tweets, data tweets), pre-processing (case folding, remove URLs, remove stop words, change into standard words, stemming, tokenization), sentiment labeling (IR in the form of regular expressions, sentiment labeling), and data visualization show pie chart, show word cloud). Of the 8993 tweets that have been analyzed, 2213 positive tweets, 1735 negative tweets, and 5045 neutral tweets were found.
Analysis of Public Sentiment of Covid-19 Dynamics on Social Media Using Support Vector Machine and Particle Swarm Optimization: Analisis Sentimen Publik Dinamika Covid-19 di Media Sosial Menggunakan Support Vector Machine dan Particle Swarm Optimization Fakhri Muhammad; Chaerur Rozikin; Riza Ibnu Adam
SYSTEMATICS Vol 4 No 2 (2022): August 2022
Publisher : Universitas Singaperbangsa Karawang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35706/sys.v4i2.7006

Abstract

Variants of covid in Indonesia continue to grow and make people required to stay at home and are not required to go out if they don't have important things, therefore many people who stay at home often play social media such as twitter, it is possible that many irresponsible people make opinions or hoaxes with a specific purpose to make tweets that are not in accordance with the facts, which are feared to make the public more panicked about the increase in this covid-19 variant. Therefore this study was conducted to classify tweets as positive, negative, and neutral. The methodology used is a text mining process with 4 modelings using Support Vector Machine and Particle Swarm Optimization. The results obtained from the 4th modeling produce an accuracy of 83% on the linear kernel. While the PSO modeling in scenario 4 with 90:10 data division resulted in the highest accuracy in linear and polynomial kernels of 86% and 87%, respectively. Other evaluation values ​​also improved, such as precision to 90%, recall to 83%, and f1-score to 86%.
Co-Authors Apriade Voutama Chaerur Rozikin Nana Mulyana Maghfur Riza Ibnu Adam