Komparasi Model Klasifikasi Sentimen Issue Vaksin Covid-19 Berbasis Platform Instagram

Authors

  • Primandani Arsi Universitas Amikom Purwokerto, Banyumas
  • Laili Nur Hidayati Universitas Amikom Purwokerto, Banyumas
  • Azizan Nurhakim Universitas Amikom Purwokerto, Banyumas

DOI:

https://doi.org/10.30865/mib.v6i1.3509

Keywords:

Covid-19, Kemenkes RI, SVM, KNN

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%.

References

M. H. Ansori, “Wabah COVID-19 dan Kelas Sosial di Indonesia,†Habibie Cent. Insights, no. 14, 2020.

Z. H. MS and A. Rizaldi, “Merespon Nalar Kebijakan Negara Dalam Menangani Pandemi Covid 19 Di Indonesia,†Ekon. dan Kebijak. Publik Indones., vol. 7, no. 1, pp. 36–53, 2020.

I. S. Joyosemito and N. M. Nasir, “Gelombang Kedua Pandemi Menuju Endemi Covid-19: Analisis Kebijakan Vaksinasi Dan Pembatasan Kegiatan Masyarakat Di Indonesia,†J. Sains Teknol. dalam Pemberdaya. Masy., vol. 2, no. 1, pp. 55–66, 2021.

A. Damayanti and K. Yuriawan, “Instagram sebagai Medium Komunikasi Risiko di Masa Pandemi COVID-19 : Studi Netnografi terhadap Komunitas Online KawalCOVID19 . id,†J. Komuikasi Pembang., vol. 18, no. 02, pp. 176–193, 2020.

M. Agustine and Y. R. Prasetyawati, “terhadap citra dapurfit,†PRofesi Humas, vol. 5, no. 1, pp. 82–97, 2020.

I. Yelin et al., “Associations of the BNT162b2 COVID-19 vaccine effectiveness with patient age and comorbidities,†medRxiv Prepr., 2021.

B. F. Haynes et al., “Prospects for a safe COVID-19 vaccine,†Sci. Transl. Med. |, vol. 0948, no. November, pp. 1–13, 2020.

E. D. Agustono, D. Sianturi, A. Taufik, and W. Gata, “Analisis Sentimen Terhadap Warga China saat Pandemi dengan Algoritma Term Frequency-Inverse Document Frequecy dan Support Vectore Machine,†J. Inform. dan Rekayasa Elektron., vol. 3, no. 2, 2020.

A. Tripathy, A. Agrawal, and S. K. Rath, “Classification of Sentimental Reviews Using Machine Learning Techniques,†in Procedia - Procedia Computer Science, 2015, vol. 57, pp. 821–829.

A. M. Zuhdi, E. Utami, and S. Raharjo, “Analisis Sentimen Twitter Terhadap Capres Indonesia 2019 Dengan MetodE K-NN,†J. Inf. Politek. Indonusa Surakarta, vol. 5, no. 2, pp. 1–7, 2019.

Q. Wang, K. Liu, and K. Ma, “Emotional Analysis of Public Opinions in Colleges and Universities : Based on Naive Bayesian Classification Method,†J. Phys., 2019.

Pristiyono, M. Ritonga, M. A. Al Ihsan, A. Anjar, and F. H. Rambe, “Sentiment analysis of COVID-19 vaccine in Indonesia using Naïve Bayes Algorithm,†in Annual Conference on Computer Science and Engineering Technology (AC2SET) 2020, 2021.

M. A. FAUZI, “Random Forest Approach fo Sentiment Analysis in Indonesian Language,†Indones. J. Electr. Eng. Comput. Sci., vol. 12, no. 1, pp. 46–50, 2018.

R. K. Thakur and M. V Deshpande, “Kernel Optimized-Support Vector Machine and Mapreduce framework for sentiment classification of train reviews,†Indian Acad. Sci., vol. 44, no. 1, pp. 1–14, 2019.

N. S. Sattar and S. Arifuzzaman, “COVID-19 Vaccination Awareness and Aftermath: Public Sentiment Analysis on Twitter Data and Vaccinated Population Prediction in the USA,†Appl. Sci., no. March 2020, 2021.

F. M. J. M. Shamrat and S. Chakraborty, “Sentiment analysis on twitter tweets about COVID-19 vaccines using NLP and supervised KNN classification algorithm,†Indones. J. Electr. Eng. Comput. Sci., vol. 23, no. 1, 2021.

E. C. Ates, E. Bostanci, and M. S. Guzel, “Comparative Performance of Machine Learning Algorithms in Cyberbullying Detection: Using Turkish Language Preprocessing Techniques,†Comput. Soc. Cornell Univ., 2021.

W. A. Luqyana, I. Cholissodin, and R. S. Perdana, “Analisis Sentimen Cyberbullying pada Komentar Instagram dengan Metode Klasifikasi Support Vector Machine,†J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 2, no. 11, pp. 4704–4713, 2018.

K. Kim, “Noise Avoidance SMOTE in Ensemble Learning for Imbalanced Data,†IEEE Access, vol. 9, pp. 143250–143265, 2021.

R. Patra and B. Khuntia, “Analysis and Prediction Of Pima Indian Diabetes Dataset Using SDKNN Classifier Technique,†in IOP Conference Series: Materials Science and Engineering, 2021.

A. A. Salih and A. M. Abdulazeez, “Evaluation of Classification Algorithms for Intrusion Detection System : A Review,†J. Soft Comput. Data Min. Eval., vol. 1, pp. 31–40, 2021.

Downloads

Published

2022-01-25

Issue

Vol. 6 No. 1 (2022): Januari 2022

Section

Articles

License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License

Authors who publish with this journal agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).