Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal International Journal of Engineering and Computer Science Applications (IJECSA)
Afrig Aminuddin
Universiti Malaysia Pahang Al-Sultan Abdullah
Computer Science & IT

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

Found 1 Documents
Search

 1 
Sentiment Analysis and Topic Modeling of Kitabisa Applications using Support Vector Machine (SVM) and Smote-Tomek Links Methods I Nyoman Switrayana; Diki Ashadi; Hairani Hairani; Afrig Aminuddin
International Journal of Engineering and Computer Science Applications (IJECSA) Vol 2 No 2 (2023): September 2023
Publisher : Universitas Bumigora Mataram-Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/ijecsa.v2i2.3406

Abstract

Kitabisa is an Indonesian application that functions to raise funds online. Users can easily support various types of campaigns and donate funds to various social causes through the app. User reviews of the application are very diverse, and it is not sure whether user reviews of the application tend to be positive, neutral, or negative. This research aimed to analyze the sentiment of the Kitabisa application by modeling topics using Latent Dirichlet Allocation (LDA) and classifying user reviews using a Support Vector Machine (SVM). The scrapped dataset showed imbalanced dataset problems, so the SMOTE-Tomek Links oversampling technique was proposed. The results of this study show that using LDA produces five topics often discussed in 750 reviews. Then, the performance of SVM without using SMOTE-Tomek Links was 72% accuracy, 76% precision, 72% recall, and 64% f1 score. Meanwhile, using SMOTE-Tomek Links could significantly improve the performance, namely 98% accuracy, 98% precision, 98% recall, and 98% f1 score. Based on this research, the application of SVM achieved high performance for user sentiment classification, especially when the dataset was in a balanced state. Therefore, the SMOTE-Tomek Links oversampling technique is recommended for dealing with unbalanced sentiment datasets.
Co-Authors Diki Ashadi Hairani Hairani I Nyoman Switrayana