<![CDATA[Easycash is an online lending platform that offers convenience and speed in the loan process, and is licensed and supervised by the Financial Services Authority (OJK). This study aims to analyze user sentiment towards the Easycash application on the Google Play Store by applying three machine learning classification algorithms, namely Support Vector Machine (SVM), Naïve Bayes, and Random Forest. The research data was obtained through a web scraping process on 10,000 application user reviews. The analysis stages include data preprocessing, consisting of data cleaning, case folding, tokenization, stopword removal, and stemming, followed by sentiment labeling using a rule-based approach, and feature extraction using the Term Frequency–Inverse Document Frequency (TF-IDF) method. The dataset is divided into two parts, namely a training set of 80% and a testing set of 20% for model performance evaluation. The test results show that the Naïve Bayes algorithm has the best performance with an accuracy rate of 85%, followed by Random Forest at 84% and Support Vector Machine at 83%. WordCloud visualizations show that words like "easy," "fast," "limit," and "good" dominate positive reviews, while words like "pay," "bill," and "interest" frequently appear in negative reviews. Based on these results, the Naïve Bayes algorithm is considered the most effective in classifying user sentiment toward the Easycash app and can be used as a basis for evaluating and improving the quality of digital financial app services in Indonesia.]]>
Copyrights © 2026
