Whatsapp App Review Sentiment Classification On Play Store Using Naïve Bayes Classifier
##plugins.themes.bootstrap3.article.sidebar##
##plugins.themes.bootstrap3.article.main##
Abstract
Currently, people can easily make remote contact with the WhatsApp application which makes it easier for users to communicate such as sending text messages, pictures, videos, voice messages, sharing files to make voice and video calls for free with internet access. WhatsApp is a digital application that can be used by the public for free, users can also provide reviews through the Google Play Store. The reviews on the Google Play Store are the opinions of users in providing input to application developers. This test aims to ascertain consumer opinions or emotions towards the WhatsApp application by applying the Naïve Bayes Classifier method in the process of classifying consumer reviews which will be used to solve for the highest score. The reviews are divided into two labels, namely positive reviews and negative reviews. Based on the tests that have been carried out, the highest accuracy results are obtained at a ratio of 90:10 with an accuracy of 81%, 74% precision and 54% recall with an unbalanced number of datasets, namely 669 positive reviews and 331 negative reviews. negative sentiment.
##plugins.themes.bootstrap3.article.details##
Anjasmoros, M. T., Istiadi, & Marisa, F. (2020). Analisis Sentimen Aplikasi Gojek menggunakan metode SVM dan NBC. Conference on Innovation and Application of Science and Technology, 1–10.
Appannie.com. (2022). State of Mobile 2022. Appannie.Com. https://anacecilia.digital/wp-content/uploads/2022/01/app_annie__state_of_mobile_2022__en.pdf
Arpit. (2021). Top 5 Reasons Showing the Importance of Ratings and Reviews for Your Mobile App. Mobileappdaily.Com. https://www.mobileappdaily.com/importance-of-mobile-app-reviews#%5C
Asnawi, M. H., Firmansyah, I., Novian, R., & Pontoh, R. S. (2021). Perbandingan Algoritma Naive Bayes , K-NN , dan SVM dalam Pengklasifikasian Sentimen Media Sosial. SEMINAR NASIONAL STATISTIKA, 1–12.
Basryah, E. S., Erfina, A., & Warman, C. (2021). Analisis Sentimen Aplikasi Dompet Digital di era 4.0 pada masa pandemi Covid-19 di Play Store menggunakan Algoritma Naive Bayes Classifier. Seminar Nasional Sistem Informasi Dan Manajemen Informatika, 189–196.
Gumilang, Z. A. N. (2018). Implementasi Naive Bayes Classifier dan Asosiasi untuk Analisis Sentimen Data Ulasan Aplikasi E-Commerce Shopee pada Situs Google Play. Universitas Islam Indonesia.
Lidwina Andrea. (2021). Jumlah Pengguna Aktif Bulanan Platform Pesan Instan (2020). Databoks. https://databoks.katadata.co.id/datapublish/2021/01/21/berapa-jumlah-pengguna-aktif-whatsapp-dan-platform-pesaingnya
Malsi, E., & Jatikusumo, D. (2022). Analisis Sentimen Terhadap Ulasan Aplikasi FLIP.ID Menggunakan Klasifikasi Naïve Bayes. Jurnal Informatika Dan Teknologi Informasi, 18(1), 1–11.
Muhammadin, A., & Sobari, I. A. (2021). Analisis Sentimen pada Ulasan Aplikasi Kredivo dengan Algoritma SVM. Jurnal Rekayasa Perangkat Lunak, 2(2), 85–91.
Nurwahyuni, S. (2019). Analisis Sentimen Aplikasi Transportasi Online KRL Access Menggunakan Metode Naive Bayes. Jurnal Swabumi, 7, 31–36. https://doi.org/10.31294/swabumi.v7i1.5575
StatCounter. (2022). Mobile Operating System Market Share Indonesia. Global Statcounter. https://gs.statcounter.com/os-market-share/mobile/indonesia
Wulandari, D. (2020). Klasifikasi Komentar pada Google Play Store dengan menggunakan Metode Modified K-Nearest Neighbor (MKNN). In State Islamic University Of Sultan Syarif Kasim Riau. Universitas Islam Negeri Sultan Syarif Kasim Riau.
Yavi, A. F. (2018). Klasifikasi Artikel Berbahasa Indonesia untuk Mendeteksi Clickbait menggunakan Metode Naïve Bayes. Journal of Information and Technology, 06(1), 141–147.
Yusra, Olivita, D., & Dkk. (2016). Perbandingan Klasifikasi Tugas Akhir Mahasiswa Jurusan Teknik Informatika Menggunakan Metode Naïve Bayes Classifier dan K-Nearest Neighbor. Jurnal Sains, Teknologi Dan Industri, 14(1), 79–85.