This Author published in this journals
All Journal TEKNIK INFORMATIKA
Zulfikar Firmansyah Firmansyah
Universitas AMIKOM Yogyakarta

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

ANALISIS SENTIMEN MASYARAKAT TERHADAP VAKSINASI COVID-19 BERDASARKAN OPINI PADA TWITTER MENGGUNAKAN ALGORITMA NAIVE BAYES Zulfikar Firmansyah Firmansyah; Nila Feby Puspitasari
JURNAL TEKNIK INFORMATIKA Vol 14, No 2 (2021): JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v14i2.24024

Abstract

Corona virus is a group of viruses that infect the respiratory tract. This virus is known as Covid-19 which is known to have originated from China, which appeared in December 2019. In early March 2020, the first time the Covid-19 virus was reported to have entered Indonesia and spread to all provinces in Indonesia. The steps taken by the government to prevent the spread of the virus include creating a Covid-19 vaccination program where this information can be obtained through social media, including Twitter, which is a popular social media in Indonesia and is currently a trending topic. Its users are free to have an opinion or opinion through posts or comments. There are various kinds of opinions from the public, there are positive, neutral, and negative opinions about the Covid-19 vaccination program.Therefore, this study can be formulated that how to respond to Indonesian public opinion on the Covid-19 vaccination program using data taken from Twitter social media and conducting sentiment analysis using the Naive Bayes algorithm by classifying positive, neutral, and negative sentiments from Twitter using keywords. namely “Vaccine” and “Covid”.The results of the research that have been carried out show that the level of system accuracy in the application of the Naïve Bayes algorithm gets an accuracy value of 78% and testing using the k-fold cross validation method gets an accuracy value of 80%.