Main Article Content

Yulinar Rizkyani Saputri
Herny Februariyanti


The growth of information and technology is causing individuals to live a more digital lifestyle, and one example of this is in the buying and selling activities that already use E-Commerce as a venue to facilitate them. Using the RStudio application and the Naive Bayes Classifier Algorithm, this study aims to find or analyze both positive and negative reviews of the e-commerce application through user reviews on Google Play. The technique employed is text mining and text processing, which involves stemming, tokenizing, case folding, normalization, and filtering steps. Review data for the Shopee app on Google Play is gathered through data scraping utilizing the web application appfollow, and review data may be saved in csv format. The acquired data will be processed using text processing, first by translating reviews in other languages to Indonesian, then by normalizing or cleaning the content to remove emoticons. The normalized data will then be uniformly converted to lower case letters as a whole in the case folding process, which comes next. Each word that has no influence or is independent, which is referred to as a token, will be isolated from the uniform data. Calculating the presence of words in the data and their frequency of occurrence is made easier by the tokenizing procedure. The Nave Bayes Classifier Method is used to compare training data and test data after text has undergone text processing to produce positive and negative sentiment classes based on the number of word frequencies.


Download data is not yet available.

Article Details

How to Cite
Saputri, Y. R. and Februariyanti, H. (2022) “SENTIMENT ANALYSIS ON SHOPEE E-COMMERCE USING THE NAÏVE BAYES CLASSIFIER ALGORITHM”, Jurnal Mantik, 6(2), pp. 1349-1357. doi: 10.35335/mantik.v6i2.2397.
[2] P. S. M. Suryani, L. Linawati, and K. O. Saputra, “Penggunaan Metode Naïve Bayes Classifier pada Analisis Sentimen Facebook Berbahasa Indonesia,” Majalah Ilmiah Teknologi Elektro, vol. 18, no. 1, p. 145, May 2019, doi: 10.24843/mite.2019.v18i01.p22.
[3] H. Februariyanti, M. Firmansyah, J. S. Wibowo, and M. S. Utomo, “Terakreditasi ‘Peringkat 4 (Sinta 4)’ oleh Kemenristekdikti,” vol. 6, no. 2, pp. 1–5, doi: 10.5281/zenodo.4399381.
[4] F. Handayani, D. Feddy, and S. Pribadi, “Implementasi Algoritma Naive Bayes Classifier dalam Pengklasifikasian Teks Otomatis Pengaduan dan Pelaporan Masyarakat melalui Layanan Call Center 110.”
[5] D. Garbian Nugroho, Y. Herry Chrisnanto, A. Wahana Jurusan Informatika, and F. Matematika dan Ilmu Pengetahuan Alam Universitas Jenderal Achmad Yani Jalan Terusan Jenderal Sudirman, ANALISIS SENTIMEN PADA JASA OJEK ONLINE MENGGUNAKAN METODE NAÏVE BAYES. 2016.
[6] RStudio, “Download RStudio IDE,”, 2022. (accessed May 25, 2022).
[7] Stackoverflow, “Remove all special characters from a string in R,”, 2021. (accessed May 27, 2022).
[8] Nur Andi Setiabudi, “Stemming Bahasa Indonesia dengan R,”, 2015. (accessed Jun. 15, 2022).
[9] Yann Ryan, “Calculating tf-idf Scores with Tidytext,”, 2021. (accessed May 27, 2022).
[10] R Project, “Strip Whitespace from a Text Document,”, 2021. (accessed May 27, 2022).
[11] John McIntosh, “Creating Word Clouds Vignette,”, Apr. 03, 2017. (accessed May 27, 2022).
[12] Michael W. Kearney, “Wordcloud,”, Aug. 23, 2015. (accessed May 27, 2022).
[13] RColorBrewer, “R/ColorBrewer.R,”, Apr. 04, 2022. (accessed May 28, 2022).
[14] sudhanshublaze, “Filter data by multiple conditions in R using Dplyr,”, Jan. 25, 2022. (accessed May 28, 2022).
[15] Suhartono and U’un Setiawati, “Metode Klasifikasi Naive Bayes, Random Forest dan Decicion Tree untuk Memprediksi Kanker Payudara Menggunakan Rstudio,”, Jan. 12, 2021. (accessed May 30, 2022).
[16] RB Fajriya Hakim, “Contoh Sederhana Aplikasi Naive Bayes dengan R,”, Sep. 23, 2019. (accessed May 30, 2022).
[17] genediazjr, “remaining stopwrods from second batch,”, Oct. 10, 2016. (accessed May 31, 2022).
[18] Nur Andi Setiabudi, “Stemming Bahasa Indonesia dengan R,”, Dec. 16, 2015. (accessed May 31, 2022).