Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal International Journal of Health, Engineering and Technology
Fikri Faisal Hibatullah
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Chemical Engineering, Chemistry & Bioengineering Dentistry Engineering Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Mechanical Engineering Medicine & Pharmacology Nursing Public Health Veterinary

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Performance Measurement Of Machine Learning (Support Vector Machine, K-Nearest Neighbors, And Naive Bayes) In Crypto Wallet Applications Fikri Faisal Hibatullah; Cecep Warman
International Journal of Health Engineering and Technology Vol. 3 No. 5 (2025): IJHET JANUARY 2025
Publisher : CV. AFDIFAL MAJU BERKAH

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55227/ijhet.v3i5.254

Abstract

This study aims to compare the performance of three classification algorithms, namely Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Naïve Bayes Classifier (NBC) in analyzing user review sentiment on crypto wallet applications available on the Google Play Store . The dataset used includes 1,500 reviews from three popular crypto wallet apps, namely Trust Wallet, MetaMask , and Bitget Wallet. Each review is grouped into three sentiment categories: positive, negative, and neutral. The results of the analysis show that Bitget Wallet got the most positive reviews, while MetaMask and Trust Wallet tended to get less favorable reviews. The study evaluated the performance of each algorithm based on several performance metrics, including accuracy, precision, recall, and F1 score. The results obtained show that the SVM algorithm provides the best performance with an accuracy of 90.5%, followed by KNN with an accuracy of 85.3%, and NBC with an accuracy of 82.1%. In addition, SVM also excels in other metrics, such as precision and recall, showing that SVM is more effective at classifying user review sentiment than the other two algorithms. Based on these results, it can be concluded that SVM is the most suitable algorithm for sentiment analysis in crypto wallet applications, which can provide deeper insights into user perceptions of these applications. This research makes an important contribution to the application of machine learning algorithms for sentiment analysis in the financial technology sector, especially for crypto wallet applications.
Co-Authors Cecep Warman