Comparison of K- N earest Neighbor (K -NN) and Naïve Bayes Algorithm for Sentiment Analysis on Google Play Store Textual Reviews

Fintech Lending/Peer-to-Peer Lending in its application has developed very rapidly. As an agricultural country, Indonesia is undoubtedly a market asset for the banking world to improve its services, especially in the capital. IGrow, as part of a crowdfunding company registered with the Indonesian Financial Services Authority (OJK), has taken an essential role in the field of agricultural capital. I Grow has a Fintech platform on the Google Play Store that has mixed reviews and opinions among users. Various opinions and reviews from users will undoubtedly have a positive and negative impact on the development of the business. The purpose of this study is to provide sentiment analysis of the IGROW platform on the Google Play Store. The method used in this study uses the K-Nearest Neighbor (K-NN) Algorithm and the Naive Bayes classification algorithm. The study results show that the accuracy, precision, and recall values of K-NN and Naive Bayes classification are (73.85%, 76.60%, 85.71 %) and (75.38%, 80.95%, 80.95%). The Naive Bayes classification produces slightly better predictions than K-NN by getting slightly better accuracy and precision values, but K-NN gets better values on recall.