Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Nasional Teknologi Informasi dan Aplikasinya
Ni Luh Putu Happy Nirmala
Unknown Affiliation
Computer Science & IT Engineering

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

Found 1 Documents
Search

 1 
Analisis Sentimen Ulasan Aplikasi M-Paspor Menggunakan TF-IDF dan Support Vector Machine Ni Luh Putu Happy Nirmala; Ida Bagus Gede Dwidasmara
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 3 No. 2 (2025): JNATIA Vol. 3, No. 2, Februari 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v03.i02.p23

Abstract

In the era of globalization, getting a passport has become an essential requirement as an official document for international travel. The Directorate General of Immigration introduced M-Paspor, a new application with more than 1 million downloads and 29 thousand reviews on the Google Play Store. This research aims to analyze the sentiments of Indonesian people using the MPaspor application using the Support Vector Machine and TF-IDF methods for weighting, as well as evaluating the model with K-fold Cross Validation in Google Colab with the Python programming language. The SVM method was chosen because of its ability to achieve high classification accuracy, while feature extraction was carried out using the TF-IDF method to determine the weight of the words in the review. The dataset consists of 3,000 review data, with 1,500 negative sentiment review data and 1,500 positive sentiment review data, which underwent a series of preprocessing stages, namely noise removal, case folding, tokenization, normalization, stopwords removal, and stemming. The SVM model used to analyze and get the best combination of parameters C:1, gamma:scale, with the kernel:rbf. Evaluation of the model with K-Fold Cross Validation shows an average accuracy of 83.62%, precision of 84.7%, recall of 83.65%, and F1 score of 83.51% 
Co-Authors Ida Bagus Gede Dwidasmara