Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Ilmu Komputer dan Agri-Informatika
Amin Elhan
IPB University
Agriculture, Biological Sciences & Forestry Computer Science & IT

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

Found 1 Documents
Search

 1 
Analisis Sentimen Pengguna Twitter terhadap Vaksinasi COVID-19 di Indonesia menggunakan Algoritme Random Forest dan BERT Amin Elhan; Medria Kusuma Dewi Hardhienata; Yeni Herdiyeni; Sony Hartono Wijaya; Julio Adisantoso
Jurnal Ilmu Komputer dan Agri-Informatika Vol 9 No 2 (2022)
Publisher : Departemen Ilmu Komputer, Institut Pertanian Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/jika.9.2.199-211

Abstract

The Covid-19 pandemic has encouraged many stakeholders to be able to adapt to current conditions. One of the programs launched by the government in order to overcome the spread of Covid-19 is to run a vaccination program. In order to find out the public's interest in the Covid-19 vaccination program that was launched, it is necessary to carry out a sentiment analysis. Sentiment analysis is generally done to obtain the latest information from a large corpus. The purpose of this study is to analyze the sentiments of Twitter users towards the Covid-19 vaccination in Indonesia using the Random Forest and BERT Algorithms. The research stages include pre-processing Twitter data related to Covid-19 vaccination topics, sentiment labeling, handling unbalanced data, classifying datasets using the Random Forest and BERT algorithms, as well as analysis and evaluation. After handling unbalanced data, the results of Twitter user sentiment analysis for Covid-19 vaccination in Indonesia yielded an accuracy of 81%, F1-score of 74%, precision of 76%, and recall of 74% using the Random Forest algorithm and an accuracy of 82%, F1-score 79%, precision of 78%, and recall of 79% using the BERT Algorithm. Although the BERT Algorithm has generally a slightly higher performance than the Random Forest Algorithm, the simulation results show that the Random Forest algorithm has significantly lower computation time compared to the BERT algorithm in the considered case.
Co-Authors Julio Adisantoso Medria Kusuma Dewi Hardhienata Sony Hartono Wijaya