Sentimen Analisis Vaksin Covid-19 Menggunakan Naive Bayes Dan Support Vector Machine

Debby Alita; RB Ali Shodiqin

doi:10.58602/jaiti.v1i1.20

Debby Alita Universitas Teknokrat Indonesia
RB Ali Shodiqin Universitas Teknokrat Indonesia

DOI: https://doi.org/10.58602/jaiti.v1i1.20

Abstract

Vaccine administration in Indonesia has now reached the booster vaccine stage, various types of vaccines have been given to the Indonesian people from the Sinovac, AstraZeneca, Sinopharm, Moderna, Pfizer vaccines, etc. Not a few Indonesian people use several types of vaccines that are offered up to booster vaccines, but there are some people who think they are still infected with this Covid virus with severe symptoms. Another opinion is that there is also a vaccine. In 2019, people were shocked by a new virus from Wuhan, China, namely the corona virus or called COVID-19 (Corona Virus Disease 2019). The government invites the public to get the Covid-19 vaccine in order to form herd immunity or group immunity to the Covid-19 virus. Sentiment analysis can be used to evaluate a service performance and so on. So the author will conduct a comparison between the Naive Bayer Classifier method and the Support Vector Machine to find out which method is more efficient in knowing people's accurate views of the Covid-19 vaccine. The performance test results of the two methods show that the performance of the Naive Bayes Classifier method (Accuracy 72.88%, Precision 43.49%, Recall 54.95%, and average performance 57.10%) is higher than the average performance of the Support Vector Machine method (Accuracy 77.00% , Precision 75.00%, Recall 7.70%, and average performance 53.52%). Based on the average performance value of the Naive Bayes Classifier method, it can be considered more efficient than the Support Vector Machine method.

Downloads

Download data is not yet available.

References

R. I. Kemenkes, “Pedoman Kesiapsiagaan Menghadapi Coronavirus Disease (COVID-19),” Direkorat Jenderal Pencegah dan Pengendali Penyakit, 2020.

U. Yaqub, N. Sharma, R. Pabreja, S. A. Chun, V. Atluri, and J. Vaidya, “Location-based sentiment analyses and visualization of Twitter election data,” Digit. Gov. Res. Pract., vol. 1, no. 2, pp. 1–19, 2020.

D. Darwis, E. S. Pratiwi, and A. F. O. Pasaribu, “Penerapan Algoritma Svm Untuk Analisis Sentimen Pada Data Twitter Komisi Pemberantasan Korupsi Republik Indonesia,” Edutic-Scientific J. Informatics Educ., vol. 7, no. 1, 2020.

R. R. SURYONO and B. Indra, “P2P Lending Sentiment Analysis in Indonesian Online,” 2020.

C. Colón-Ruiz, “Semi-Supervised Generative Adversarial Network for Sentiment Analysis of drug reviews.” Institute of Electrical and Electronics Engineers (IEEE), 2021, doi: 10.36227/techrxiv.17075054.

C. Du and L. Huang, “Sentiment Analysis Method based on Piecewise Convolutional Neural Network and Generative Adversarial Network,” International Journal of Computers Communications & Control, vol. 14, no. 1. Agora University of Oradea, pp. 7–20, 2019, doi: 10.15837/ijccc.2019.1.3374.

I. Ahmad, H. Sulistiani, and H. Saputra, “The Application Of Fuzzy K-Nearest Neighbour Methods for A Student Graduation Rate,” Indones. J. Artif. Intell. Data Min., vol. 1, no. 1, pp. 47–52, 2018.

D. Alita, Y. Fernando, and H. Sulistiani, “Implementasi Algoritma Multiclass SVM pada Opini Publik Berbahasa Indonesia di Twitter,” J. Tekno Kompak, vol. 14, no. 2, pp. 86–91, 2020.

S. Setiawansyah, Q. J. Adrian, and R. N. Devija, “Penerapan Sistem Informasi Administrasi Perpustakaan Menggunakan Model Desain User Experience,” J. Manaj. Inform., vol. 11, no. 1, pp. 24–36, 2021.

M. N. D. Satria, “Application of SAW in the Class Leader Selection Decision Support System,” Chain J. Comput. Technol. Comput. Eng. Informatics, vol. 1, no. 1, pp. 27–31, 2023.