Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal JURNAL MEDIA INFORMATIKA BUDIDARMA
Laili Nur Hidayati
Universitas Amikom Purwokerto, Banyumas
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

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

Found 1 Documents
Search

 1 
Komparasi Model Klasifikasi Sentimen Issue Vaksin Covid-19 Berbasis Platform Instagram Primandani Arsi; Laili Nur Hidayati; Azizan Nurhakim
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 6, No 1 (2022): Januari 2022
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v6i1.3509

Abstract

Information about COVID-19 or regulations regarding it has been massively shared by the Ministry of Health, via kemenkes_ri account. Including the topic of vaccinations. Although health research has been conducted to support the covid-19 vaccine campaign, however there are still people who give negative comments. Sentiment is also found in the kemenkes_ri account. Sentiment analysis is an opinion classification process to determine the responses given are included in the positive, negative or neutral categories. In this study, it is proposed to compare the performance of the SVM and KNN algorithms to classify sentiment in the kemenkes_ri account related to vaccine policy in Indonesia. Sentiment is classified into 3 polarities namely neutral, positive, and negative. The purpose of this comparison is to compare the best classification model on the topic of vaccine issue sentiment analysis, especially the Instagram platform. In this study, the stages started from the comment scrapping technique which resulted in 2,925 records. Preprocessing using NLP technique and weighting using TF-IDF technique. Next, the SMOTE technique was performed to avoid imbalancing class. The ratio of training and testing data is 9:1. The results showed that the best classification is SVM = 98.30%, while the KNN method is 80.03%.
Co-Authors Azizan Nurhakim Primandani Arsi