<![CDATA[In today's technological era, the internet has played an important role in all aspects of human life. This is also what drives various mobile applications to develop very rapidly. Kredivo is an instant credit solution that provides convenience to buy now pay later in a 1-month tenor or 3-month installment tenor with 0% interest. In addition, Kredivo is not only used for shopping purposes, but borrowers can also make withdrawals in the form of cash. However, not all users are satisfied with the service of the application. and the many comments submitted through the Kredivo application review feature on the Google Play Store. Therefore, in this study, researchers tried to conduct a sentiment analysis of Kredivo application users using the K-Nearest Neighbor algorithm. The purpose of this study was to determine the accuracy value produced by the K-Nearest Neighbor algorithm. From testing 1880 data using the cross-validation model, it was found that reviews containing positive sentiment were 62.55% and containing negative sentiment were 37.45%. Evaluation of the classification results using the Confusion Matrix test obtained an accuracy value of 79.36%, with a recall value of 83.08%, precision of 72.15%, and recall (Specificity) of 73.15%, so it can be concluded that the K-Nearest Neighbor algorithm can classify sentiments well using review data on Kredivo application users]]>
Copyrights © 2024
