Klasifikasi Pendapat Masyarakat Terhadap Penggunaan Vaksin Dalam Mengantisipasi Covid-19 Menggunakan Teknik Sentiment Analisis Berbasis Naïve Bayes

Widya Damayanti; Bagus Setya Rintyarna; Wiwik Suharso

Authors

Widya Damayanti Universitas Muhammadiyah Jember
Bagus Setya Rintyarna Universitas Muhammadiyah Jember
Wiwik Suharso Universitas Muhammadiyah Jember

Keywords:

Covid-19, Naïve Bayes, Multinomial Naïve Bayes, Chi-Square

Abstract

The Covid-19 pandemic is not over yet. Vaccinations that have been carried out so far are still getting pros and cons among the public. This study contains an analysis of public opinion on vaccination using the Naive Bayes-based method which was collected from the Twitter timeline from February 23 to March 9, 2021. The number of opinions that were successfully collected and used as data in this study were 1000 tweet data which were divided into 200 test data tweets. validation and 800 training data tweets. This study also uses Chi-Square as a feature selection method. The algorithms used in this research are Naive Bayes and Multinomial Naive Bayes. From the measurement results on the tests carried out, the Naive Bayes method obtained an accuracy value of 66%, precision of 79% and recall of 62%. While the Multinomial Naive Bayes method obtains an accuracy value of 71%, a precision of 81% and a recall of 68%. Based on the results obtained, the Multinomial Naive Bayes algorithm has a better performance than Naive Bayes.

References

Bruno Trstenjaka, Sasa Mikacb, Dzenana Donkoc. 2013. KNN with TF-IDF Based Framework for text Categorization, Procedia Engineering 69 (2014) 1356 – 1364.

Dirkareshza, Rianda, et al. "PENDAMPINGAN MASYARAKAT MENGENAI DAMPAK HUKUM PENOLAKAN VAKSINASI DI MASA PANDEMI COVID-19." JMM (Jurnal Masyarakat Mandiri) 5.5 (2021): 2812-2823.

Hidayatullah, Fajar, Fadibah Setiawan, and Farida Megalini. "Survei Aktivitas Dan Kebiasaan Masyarakat Serta Tingkat Resikonya Dalam Menghadapi Wabah COVID-19 Di Indonesia." Civic-Culture: Jurnal Ilmu Pendidikan PKN dan Sosial Budaya 4.1 Extra (2020): 17-31.

Kompas.Com, 2019. Pengguna Aktif Harian Twitter Indonesia Diklaim Terbanyak [Online] (Updated 30 October 2019) Available At: Https://Tekno.Kompas.Com/Read/2019/10/30/16062477/PenggunaAktif-Harian-Twitter-Indonesia-Diklaim-Terbanyak. (Diakses Pada Tanggal 19 Januari 2021).

Lasmita, Yuni, Misnaniarti Misnaniarti, and Haerawati Idris. "ANALISIS PENERIMAAN VAKSINASI COVID-19 DI KALANGAN MASYARAKAT." Jurnal Kesmas (Kesehatan Masyarakat) Khatulistiwa 8.4 (2021): 195-204.

Liu, M., Yang, J., 2012) An Improvement of TFIDF weighting in text categorization. International Proceedings of Computer Science and Information Technology, 47, pp. 44 -47

Marbella, Hendry Naufal, et al. "Analisis Pengaruh Berita Bohong di Sosial Media Terhadap Keputusan Masyarakat Indonesia Melakukan Vaksinasi Covid-19." Jurnal Indonesia Sosial Teknologi 2.11 (2021): 1951-1966. [4]

Nur, M. Y., & Santika, D. D. (2011). Analisis Sentimen Pada Dokumen Berbahasa Indonesia Dengan Pendekatan Support Vector Machine. Konferensi Nasional Sistem Dan Informatika.

RINTYARNA, BAGUS SETYA, et al. "Mapping acceptance of indonesian organic food consumption under COVID-19 pandemic using sentiment analysis of Twitter dataset." Journal of Theoretical and Applied Information Technology 99.05 (2021).

Rintyarna, Bagus Setya. "(Dokumen) Evaluating The Performance of Sentence Level Features and Domain Sensitive Features of Product Reviews on Supervised Sentiment Analysis Task." Journal of Big Data (2019).

Rintyarna, Bagus Setya. "Peer Review dan Similarity Artikel" Automatic Ranking System of University based on Technology Readiness Level Using LDA-Adaboost. MH"." International Conference on Information and Communication Technology. AMIKOM Yogyakarta, 2018.