Esi Hairani, Ira Nurpalah
This paper aims to conduct sentiment analysis on the Muslim Pro application on Google Play using the Multinomial Naive Bayes method. The underlying problem of this research is the difficulty users face in managing and understanding the information from the numerous reviews. With over 100 million downloads, developers must understand user sentiment to improve the application according to their needs. The dataset used consists of 3,000 reviews, which are classified into positive and negative reviews based on user ratings. The data preprocessing process includes case folding, tokenization, normalization, stopword removal, and stemming. The division of training data and test data in this study is 80:20. The results of the study show that the Multinomial Naive Bayes method achieves an accuracy of 90%, with a precision of 92%, a recall of 91%, and an F1 score of 92%. These results indicate that the Multinomial Naive Bayes method effectively classifies reviews of the Muslim Pro application, assisting the company in making effective decisions and developing an application that meets user needs. © 2024 IEEE.
Islamic Religious Education, Institut Ilmu Quran, Jawa Barat, Banten, Indonesia; Information Systems and Technology Education, Universitas Pendidikan Indonesia, Jawa Barat, Purwakarta, Indonesia
Research at a Glance
Register to unlock
Topics & SDG Alignment
Register to unlock
Collaboration
Register to unlock
Author Profile (Selected)
Register to unlock
References Overview
Register to unlock
Journal & Source
Register to unlock
Metadata & Integrity
Register to unlock