ANALISIS SENTIMEN APLIKASI BSI MOBILE PADA ULASAN GOOGLE PLAY MENGGUNAKAN ALGORITMA NAIVE BAYES

Muhammad Bahaudin Mahmud, NIM.: 19106050035 (2023) ANALISIS SENTIMEN APLIKASI BSI MOBILE PADA ULASAN GOOGLE PLAY MENGGUNAKAN ALGORITMA NAIVE BAYES. Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (ANALISIS SENTIMEN APLIKASI BSI MOBILE PADA ULASAN GOOGLE PLAY MENGGUNAKAN ALGORITMA NAIVE BAYES) 19106050035_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (1MB) | Preview
	Text (ANALISIS SENTIMEN APLIKASI BSI MOBILE PADA ULASAN GOOGLE PLAY MENGGUNAKAN ALGORITMA NAIVE BAYES) 19106050035_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (4MB) | Request a copy

Abstract

BSI Mobile is a mobile banking application where BSI customers can easily make online transactions via their smartphones. The BSI Mobile application is a relatively new application, so there are several weaknesses or complaints about the application from customers. To find out the opinions of these customers, you can see the reviews given in the reviews feature on Google Play. Therefore, research was conducted on sentiment reviews of the BSI Mobile application with the naïve Bayes algorithm. In this study, 2000 training data were used with an even comparison between positive and negative. The model that has captured the complete stages, namely with stopword removal, has an accuracy of 97%, while the model with stages without using stopword removal has a greater accuracy of 98% using a confusion matrix. Implementation of the model that has been formed, classification is carried out on unlabeled test data in the amount of 4527 review data. This classification results in 57.3% of data labeled positive and 42.7% labeled negative.

Share this knowledge with your friends :

Actions (login required)

View Item