Sentiment Analysis of Covid Vaccination Policy In Indonesia Using Random Forest

DOI

10.2991/978-94-6463-338-2_31How to use a DOI?

Keywords

Sentiment Analysis; Covid; Random Forest; Data Mining

ABSTRACT

The World Health Organization (WHO) on March 11, 2020, has declared the novel coronavirus (COVID-19) outbreak a global pandemic and Presidential Decree of the Republic of Indonesia Number 12 of 2020 concerning the Determination of Non-Natural Disasters for the Spread of CORONA VIRUS DISEASE 2019 (COVID-19) as a National Disaster and vaccinating its citizens starting on January 13, 2021, but community is divided into two, there are those who agree with the government's policy and some who do not agree with the government's policy, besides that there are also those who are forced to accept it because the covid vaccine has become a requirement in state life, for travel, for work, entertainment and so on. With the difference of opinion among the public, a sentiment analysis study was conducted to see how high the level of accuracy was based on the level of data ranging from 500 data, 1000 data, 2000 data, 3000 data and 4000 using the Random Forest method. Data collection was carried out from January to September 2021 from Republic Indonesia’s Ministry of Health Fanpage and retrieve 100-500 random data every month. There are 4 stages Preprocessing : cleaning, case folding, filtering, and tokenizing, and labelling with positive, netral and negative. The results of the model test show the highest F1-Score level in the data with a total of 2000 with a combination of uni-tri Gram tokenization. Meanwhile, the lowest F1-Score level is when the model uses 500 data with unigram tokenization. The use of more than 2000 data in the formation of the model using the random forest method showed a significant decrease in the F1-Score level. The experimental results show that when the 4000 data used with uni-tri gram tokenization concatenation has a lower F1-Score level, even almost the same as the F1-score level in 1000 data without using a tokenization combination. In general, the results of model testing using the Random Forest method show an increase in the F1-Score level when using a combination of uni-tri gram tokenization with less than 2000 data used.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Nurirwan Saputra
AU  - Ahmad Riyadi
AU  - Meilany Nonsi Tentua
PY  - 2023
DA  - 2023/12/23
TI  - Sentiment Analysis of Covid Vaccination Policy In Indonesia Using Random Forest
BT  - Proceedings of the 2023 International Conference on Information Technology and Engineering (ICITE 2023)
PB  - Atlantis Press
SP  - 205
EP  - 209
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-338-2_31
DO  - 10.2991/978-94-6463-338-2_31
ID  - Saputra2023
ER  -