<![CDATA[User reviews on Google Play Store provide valuable information regarding application service quality and user satisfaction. This study aims to compare the performance of the K-Nearest Neighbor (KNN) and Naïve Bayes algorithms for sentiment analysis of reviews of the Profits Anywhere application, a digital business platform offering affiliate marketing and financial services. A total of 1,037 reviews were collected through web scraping and subsequently underwent data cleaning and validation, resulting in 957 valid reviews used in the analysis, consisting of 674 positive and 283 negative reviews. The dataset was subjected to a comprehensive text preprocessing pipeline, including text cleaning, case folding, tokenization, stopword removal, and stemming, followed by feature representation using the Term Frequency–Inverse Document Frequency (TF-IDF) technique. The data were partitioned using an 80:20 stratified train–test split, while hyperparameter optimization was conducted using GridSearchCV with 5-fold stratified cross-validation. Experimental results demonstrate that KNN outperformed Naïve Bayes on the evaluated dataset and experimental configuration, achieving an accuracy of 92.19%, weighted precision of 92.23%, weighted recall of 92.19%, and weighted F1-score of 92.21%. In contrast, Naïve Bayes achieved an accuracy of 88.54%, weighted precision of 89.04%, weighted recall of 88.54%, and weighted F1-score of 88.70%. These findings provide empirical evidence regarding algorithm selection for sentiment analysis of application reviews in the fintech and digital business domains.]]>
