Analysis of Electronic Wallet User Sentiment on Twitter (x) Social Media Using the Naïve Bayes Classifier Algorithm

Abstrak

Electronic wallets are one of the most popular payment methods in Indonesia with the number of users increasing significantly in recent years, including DANA, GoPay, and LinkAja. Along with the increasing number of users, the need to analyze user opinions and comments on social media, especially on Twitter (X) is also increasing. This study uses an experimental method with data collection from Twitter (X) using data crawling techniques. The dataset used is 1,500 data with 1 attribute. This study aims to analyze user sentiment towards electronic wallets using the Naive Bayes Classifier algorithm with the Python programming language. The results of the study showed that DANA had a negative sentiment of 16.6%, a neutral sentiment of 9.0%, and a positive sentiment of 74.4%. Followed by GoPay with a negative sentiment of 9.4%, a neutral sentiment of 11.4%, and a positive sentiment of 79.2%. Meanwhile, LinkAja had the lowest negative sentiment of 8%, with a neutral sentiment of 12.2% and a positive sentiment of 79.8%. The implementation of the Naive Bayes Classifier algorithm achieved an accuracy rate of 72% for DANA, 88% for GoPay, and 88%, for LinkAja.