Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Jurnas Nasional Teknologi dan Sistem Informasi Jurnal Testing dan Implementasi Sistem Informasi
Rahmat Izwan Heroza
University of Essex
Computer Science & IT Decision Sciences, Operations Research & Management

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Analysis of User Reviews for The Mytelkomsel App Using Naïve Bayes and Random Forest Methods M. Rudi Sanjaya; Annisa Khoiriah; Rahmat Izwan Heroza; Bayu Wijaya Putra
Jurnal Testing dan Implementasi Sistem Informasi Vol. 4 No. 1 (2026): Jurnal Testing dan Implementasi Sistem Informasi
Publisher : Lembaga Riset dan Inovasi Almatani

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55583/jtisi.v4i1.2220

Abstract

While sentiment analysis of local application reviews predominantly utilizes native Indonesian data, these datasets frequently suffer from colloquial ambiguities and informal structures that degrade classifier performance. This study addresses this gap by implementing a language-filtering mechanism to separate and analyze English and Indonesian user opinions from the MyTelkomsel application, specifically justifying the inclusion of English reviews due to their superior grammatical structure and syntactic consistency, which inherently enhances feature extraction. A systematic methodology was employed, encompassing data collection from the Google Play Store, comprehensive pre-processing (case folding, tokenization, stopword removal, and stemming), and Term Frequency-Inverse Document Frequency (TF-IDF) vectorization. Evaluated using Naïve Bayes and Random Forest algorithms on 25,000 customer feedbacks, the models were compared across accuracy, precision, recall, and F1-score. The empirical results demonstrated that Random Forest outperformed Naïve Bayes, achieving a higher accuracy of 86.85% compared to 86.36%. This superiority stems from Random Forest’s robust capability to mitigate class imbalance and minimize error distribution across sentiment categories. Ultimately, this approach provides precise, actionable insights into service quality, enabling Telkomsel to effectively distinguish user satisfaction, target operational improvements, and mitigate customer churn.
Analysis of User Reviews for The Mytelkomsel App Using Naïve Bayes and Random Forest Methods M. Rudi Sanjaya; Annisa Khoiriah; Rahmat Izwan Heroza; Bayu Wijaya Putra
Jurnal Testing dan Implementasi Sistem Informasi Vol. 4 No. 1 (2026): Jurnal Testing dan Implementasi Sistem Informasi
Publisher : Lembaga Riset dan Inovasi Almatani

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55583/jtisi.v4i1.2220

Abstract

While sentiment analysis of local application reviews predominantly utilizes native Indonesian data, these datasets frequently suffer from colloquial ambiguities and informal structures that degrade classifier performance. This study addresses this gap by implementing a language-filtering mechanism to separate and analyze English and Indonesian user opinions from the MyTelkomsel application, specifically justifying the inclusion of English reviews due to their superior grammatical structure and syntactic consistency, which inherently enhances feature extraction. A systematic methodology was employed, encompassing data collection from the Google Play Store, comprehensive pre-processing (case folding, tokenization, stopword removal, and stemming), and Term Frequency-Inverse Document Frequency (TF-IDF) vectorization. Evaluated using Naïve Bayes and Random Forest algorithms on 25,000 customer feedbacks, the models were compared across accuracy, precision, recall, and F1-score. The empirical results demonstrated that Random Forest outperformed Naïve Bayes, achieving a higher accuracy of 86.85% compared to 86.36%. This superiority stems from Random Forest’s robust capability to mitigate class imbalance and minimize error distribution across sentiment categories. Ultimately, this approach provides precise, actionable insights into service quality, enabling Telkomsel to effectively distinguish user satisfaction, target operational improvements, and mitigate customer churn.
Komparasi Kinerja Algoritma Naive Bayes, SVM, dan Random Forest dalam Analisis Sentimen Aplikasi Crowdfunding Rafika Octaria Ningsih; Dwi Rosa Indah; Ardina Ariani; Mgs Afriyan Firdaus; Rahmat Izwan Heroza; M Husni Syahbani
Jurnal Nasional Teknologi dan Sistem Informasi Vol 12 No 2 (2026): Agustus 2026
Publisher : Departemen Sistem Informasi, Fakultas Teknologi Informasi, Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/TEKNOSI.v12i2.2026.231-241

Abstract

Ulasan pengguna pada platform crowdfunding merepresentasikan pengalaman, tingkat kepuasan, serta berbagai kendala yang dihadapi pengguna, sehingga memiliki nilai strategis sebagai bahan evaluasi dalam pengembangan kualitas layanan. Penelitian ini difokuskan pada analisis sentimen ulasan pengguna aplikasi Kitabisa sekaligus melakukan perbandingan kinerja algoritma Naive Bayes, Support Vector Machine (SVM), dan Random Forest dengan menerapkan framework CRISP-DM. Data penelitian berupa 1.624 ulasan pengguna yang dihimpun dari Google Play Store melalui metode web scraping. Pada tahap data preparation, data diolah melalui proses pembersihan, normalisasi teks, tokenisasi, penghapusan stopword, stemming, serta pembobotan fitur menggunakan TF-IDF. Selanjutnya, untuk mengatasi ketimpangan distribusi kelas sentimen, digunakan Synthetic Minority Over-sampling Technique (SMOTE) agar model mampu mempelajari pola data secara lebih seimbang. Proses pemodelan dilakukan dengan membagi dataset ke dalam data latih dan data uji dengan perbandingan 80:20, kemudian dievaluasi menggunakan metrik akurasi, presisi, recall, F1-score, serta k-Fold Cross Validation. Hasil pengujian mengindikasikan bahwa algoritma SVM menunjukkan performa paling unggul dengan tingkat akurasi pada data uji sebesar 94,51% serta rata-rata akurasi k-Fold sebesar 95,30%, disertai nilai standar deviasi terendah dibandingkan algoritma lainnya. Selain itu, analisis topik berbasis Latent Dirichlet Allocation (LDA) memperlihatkan bahwa sentimen positif didominasi oleh topik manfaat aplikasi dan kemudahan dalam berdonasi, sedangkan sentimen negatif umumnya berkaitan dengan kendala teknis, seperti proses verifikasi akun dan gangguan transaksi. Hasil Penelitian ini diharapkan dapat menjadi dasar pertimbangan bagi pengembang dalam meningkatkan kualitas layanan aplikasi Kitabisa.
Co-Authors Ardina Ariani Bayu Wijaya Putra Dwi Rosa Indah Khoiriah, Annisa M Husni Syahbani M. Rudi Sanjaya Mgs Afriyan Firdaus Rafika Octaria Ningsih