Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Jurnal AbdiMas Nusa Mandiri Fahma : Jurnal Informatika Komputer, Bisnis dan Manajemen
Untung Subagyo
STMIK El Rahma Yogyakarta
Computer Science & IT Decision Sciences, Operations Research & Management Education Energy Engineering Environmental Science Mathematics Physics Social Sciences Other

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

Found 3 Documents
Search

 1 
WORKSHOP PEMBUATAN WEBSITE PROFIL LARAVEL-FILAMENT DENGAN AI UNTUK LANDING PAGE DAN PUBLIKASI GITHUB Untung Subagyo; Miftahul Jannah
Jurnal AbdiMas Nusa Mandiri Vol. 8 No. 1 (2026): Periode Januari 2026
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/abdimas.v8i1.7418

Abstract

This community service program reports a two-day, project-based workshop on building a profile website with Laravel and the Filament admin panel, followed by publishing to GitHub for vocational high-school students. Objectives were to strengthen industry-relevant CRUD skills and instill version-control practices for portfolio building. The method combined short lectures, live coding, guided hands-on practice, AI-assisted generation of Bootstrap-based HTML for the landing page (via ChatGPT and Gemini), repository publication, and mini presentations. Participants were 66 students across two classes (Day-1 Class A: 32; Day-2 Class B: 34). Data included parallel-form pre/post tests, product rubrics, and satisfaction questionnaires. AI use was limited to landing-page HTML and layout suggestions; outputs were manually curated for accuracy and disclosed in project READMEs. Results show 61/66 students (92.4%) completed a minimal CRUD feature set via Filament Resources and 53/66 (80.3%) published structured repositories with informative READMEs. Average knowledge scores improved from 54 (pre) to 89 (post), yielding a normalized gain of ~0.76 (high). Mean satisfaction was ~88%. Operational issues on Day 1, uneven software readiness and bandwidth, were mitigated on Day 2 through pre-checks, offline packages, ready-to-run templates, role-based facilitation, and Composer mirrors. The program concludes that the workshop effectively advances vocational competencies in modern PHP web development and produces tangible artifacts (applications and repositories) students can extend and showcase for internships or entry-level opportunities.
Perbandingan Naïve Bayes dan Support Vector Machine pada Klasifikasi Sentimen Tokopedia Di Playstore Igo Fiqi Nurwahid; Untung Subagyo
Jurnal Informatika Komputer, Bisnis dan Manajemen Vol 24 No 3 (2026): September 2026
Publisher : LPPM STMIK El Rahma Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61805/fahma.v24i3.230

Abstract

Tokopedia is one of the largest e-commerce platforms in Indonesia, generating a growing number of user reviews that makes manual sentiment analysis inefficient. This study compares the performance of Naïve Bayes and Support Vector Machine (SVM) in classifying sentiment in Tokopedia application reviews. Data were collected using the google-play-scraper library and automatically labeled based on user ratings, with ratings of 1–2 classified as negative and 4–5 as positive. After preprocessing, including case folding, cleaning, tokenization, stopword removal, and stemming using Sastrawi, 1,212 reviews were obtained, comprising 609 negative and 603 positive reviews. Text features were extracted using TF-IDF, and the models were evaluated using 5-fold cross-validation. With default parameters, Naïve Bayes and SVM achieved accuracies of 75.99% and 74.83%, respectively. After GridSearchCV tuning, Naïve Bayes achieved 76.65% accuracy and 73.28% F1-score, while SVM achieved 77.81% accuracy and 76.51% F1-score. These results show that hyperparameter tuning affects model comparison, with tuned SVM slightly outperforming Naïve Bayes.
Analisis Sentimen Ulasan Produk Pada Marketplace Shopee Menggunakan Metode Naive Bayes Abelta Cesharilo; Untung Subagyo
Jurnal Informatika Komputer, Bisnis dan Manajemen Vol 24 No 3 (2026): September 2026
Publisher : LPPM STMIK El Rahma Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61805/fahma.v24i3.235

Abstract

Shopee is a widely used marketplace for online transactions, where product reviews allow users to share their opinions on purchased items. The large volume of reviews makes manual analysis difficult, while previous studies often overlook the normalization of informal language. This study analyzes sentiment in Shopee product reviews using Multinomial Naïve Bayes (MNB) with TF-IDF weighting and custom text normalization, comparatively evaluated against Support Vector Machine (SVM) and validated using 5-fold cross-validation. The dataset consists of 500 balanced reviews (250 positive and 250 negative) obtained from Kaggle. Preprocessing includes case folding, cleansing, normalization, tokenization, stopword removal, and stemming. Hold-out evaluation (80:20) shows that SVM achieves 96.00% accuracy, 92.59% precision, 100.00% recall, and a 96.15% F1-score, while MNB achieves 91.00% accuracy, 84.75% precision, 100.00% recall, and a 91.74% F1-score. Five-fold cross-validation yields mean accuracies of 90.80% (±3.25%) for MNB and 89.60% (±2.50%) for SVM. These results indicate that TF-IDF with custom text normalization provides stable classification performance for e-commerce reviews.
Co-Authors Abelta Cesharilo Igo Fiqi Nurwahid Miftahul Jannah