Perbandingan Algoritma Klasifikasi Svm Dan Naive Bayes Dalam Analisis Sentimen Pembelajaran Daring Di Masa Pandemi Covid-19 Di Twitter
DOI:
https://doi.org/10.34818/eoe.v9i3.18037Abstract
Abstrak Pandemi Covid-19 menciptakan banyak perubahan, salah satunya adalah sistem pendidikan di Indonesia. Yang semula sistem pendidikan yang dilaksanakan adalah pembelajaran secara tatap muka atau datang ke sekolah. Namun setelah pandemi, pembelajaran dilakukan secara daring dan dilaksanakan di rumah masing-masing. Perubahan yang mendadak serta berskala nasional ini menciptakan banyak sekali opini di masyarakat terutama opini yang berada di media sosial twitter. Pada penelitian ini bertujuan untuk menganalisis sentimen masyarakat terhadap pembelajaran daring pada masa pandemi COVID-19 di Indonesia dengan membandingkan metode klasifikasi SVM dan Naive Bayes. Dengan harapan dapat mengetahui metode mana yang paling baik performansinya. Dari penelitian ini dihasilkan metode SVM lebih baik dari pada Naive Bayes dengan nilai terbaik yang didapatkan oleh metode SVM adalah dengan presentasi 60/40 dan tanpa menggunakan sentimen netral serta menggunakan kernel RBF mendapatkan akurasi 0,72 atau 72%. Kata Kunci: covid-19, daring, opini, sentimen, naïve bayes, svmReferences
[1] S. T. P. COVID-19, “Data Sebaran COVID19 Indonesia,” covid19.go.id, 2020.
https://covid19.go.id/ (accessed May. 1,
2020).
[2] Sundus Hassan, Muhammad Rafi,
Muhammad Shahid Shaikh “Comparing
SVM and Naïve Bayes Classifiers for Text
Categorization with Wikitology as
knowledge enrichment,” IEEE 14th
International Multitopic Conference, 2012,
doi: 10.1109/INMIC.2011.6151495.
[3] A. M. Rahat, A. Kahir and A. K. M. Masum,
"Comparison of Naive Bayes and SVM
Algorithm based on Sentiment Analysis
Using Review Dataset," 2019 8th
International Conference System Modeling
and Advancement in Research Trends
(SMART), 2019, pp. 266-270, doi:
10.1109/SMART46866.2019.9117512.
[4] Samsir, Ambiyar, Unung Verawardina,
Firman Edi, Ronal Watrianthos, “Analisis
Sentimen Pembelajaran Daring Pada Twitter
di Masa Pandemi COVID-19 Menggunakan
Metode Naïve Bayes,” Jurnal Media
Informatika Budidarma, vol. 5, no. 1, pp.
157–163, 2021, doi:
10.30865/mib.v5i1.05.2604.
[5] Muhammad Zidny Naf’an and Indra
Hidayatulloh, “Ekstraksi TF-IDF NGRAM
dari Komentar Pelanggan Produk
Smartphone pada Website E- 29 commerce,”
Seminar Nasional Teknologi Informasi dan
Multimedia, vol. 6, 2018, ISSN : 2302-3805.
[6] Ravinder Ahujaa, Aakarsha Chuga, Shruti
Kohlia, Shaurya Guptaa, Pratyush Ahujaa,
"The Impact of Features Extraction on the
Sentiment Analysis," in International
Conference on Pervasive Computing
Advances and Applications – PerCAA 2019,
vol. 152, pp. 341-348, 2019, doi:
10.1016/j.procs.2019.05.008.
[7] Xiaochen Zheng , Meiqing Wang, Joaquín
Ordieres-Meré, "Comparison of Data
Preprocessing Approaches for Applying
Deep Learning to Human Activity
Recognition in the Context of Industry 4.0,"
in Sensors (SENSORS-BASEL), vol. 18,
2018, doi: /10.3390/s18072146
[8] İ. İşeri, Ö. F. Atasoy and H. Alçiçek,
"Sentiment classification of social media data
for telecommunication companies in
Turkey," 2017 International Conference on
Computer Science and Engineering
(UBMK), Antalya, 2017, pp. 1015-1019.
[9] Robbi Rahim, Nuning Kurniasih,
Muhammad Dedi Irawan, Yustria Handika
Siregar, "Latent Semantic Indexing for
Indonesian Text Similarity" International
Journal of Engineering & Technology, 2018,
Vol 7, pp.73-77. doi:
10.14419/ijet.v7i2.3.12619
[10] A. Wibowo Haryanto, E. Kholid Mawardi,
and Muljono, “Influence of Word
Normalization and Chi-Squared Feature
Selection on Support Vector Machine Text
Classification,” Proc. - 2018 Int. Semin.
Appl. Technol. Inf. Commun. Creat. Technol.
Hum. Life, iSemantic 2018, pp. 229–233,
2018, doi:
10.1109/ISEMANTIC.2018.8549748.
[11] H. Zhang, “Exploring conditions for the
optimality of naïve bayes,” Int. J. Pattern
Recognit. Artif. Intell., vol. 19, no. 2, pp.
183–198, 2005, doi:
10.1142/S0218001405003983.
[12] Ainun Fauziyah Bahary, Yuliant Sibaroni,
Mohamad Syahrul Mubarok, "Sentiment
analysis of student responses related to
information system services using
Multinomial Naïve Bayes (Case study:
Telkom University)," in 2nd International
Conference on Data and Information Science,
2019, doi:10.1088/1742-
6596/1192/1/012046.
[13] Suhariyanto, A. Firmanto and R. Sarno,
"Prediction of Movie Sentiment Based on
Reviews and Score on Rotten Tomatoes
Using SentiWordnet," 2018 International
Seminar on Application for Technology of
Information and Communication, 2018, pp.
202-206, doi:
10.1109/ISEMANTIC.2018.8549704.
