Article Per Year (5 Year)
p-Index From 2021 - 2026
1.152
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Komunikasi Jurnal Ekonomi dan Studi Pembangunan (Journal of Economics and Development Studies) JURNAL ILMIAH GEOMATIKA JCES (Journal of Character Education Society) Jurdimas (Jurnal Pengabdian Kepada Masyarakat) Royal INFOKUM Jurnal Teknologi Sistem Informasi dan Sistem Komputer TGD Jurnal SAINTIKOM (Jurnal Sains Manajemen Informatika dan Komputer) ULINA: Jurnal Pengabdian kepada Masyarakat Complex : Jurnal Multidisiplin Ilmu Nasional Scripta Technica: Journal of Engineering and Applied Technology Artificial Intelligence and Computing
Dede Prabowo Wiguna
Universitas Mandiri Bina Prestasi
Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Mechanical Engineering Social Sciences

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Analisis Sentimen E-Commerce di Indonesia dengan Algoritma Naive Bayes (Studi Kasus Pada Platform Shopee, Tokopedia, Bukalapak, dan Lazada) Dede Prabowo Wiguna; Sakaria Efrata Ginting
AICOM: Artificial Intelligence and Computing Vol. 1 No. 04 (2026): ISSUE MARET
Publisher : AICOM: Artificial Intelligence and Computing

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Penelitian ini bertujuan untuk mengklasifikasikan sentimen ulasan pelanggan pada platform e-commerce (Shopee, Tokopedia, Bukalapak, dan Lazada) guna mengevaluasi tingkat kepuasan pengguna secara otomatis. Metode yang digunakan adalah algoritma Naive Bayes dengan pembobotan kata TF-IDF, yang diimplementasikan pada dataset sebanyak 40.000 ulasan dari Kaggle Dataset. Proses penelitian mencakup tahapan preprocessing yang terdiri dari cleaning, case folding, tokenizing, filtering, dan stemming. Hasil penelitian menunjukkan bahwa model pada algoritma Naive Bayes mampu mencapai tingkat akurasi sebesar 84,88%. Berdasarkan analisis distribusi sentimen, aplikasi Shopee memperoleh ulasan positif terbanyak (6.769 ulasan), sedangkan Bukalapak menerima ulasan negatif tertinggi (4.365 ulasan). Meskipun sangat efektif dalam membedakan sentimen positif dan negatif, model ini belum mampu mengidentifikasi sentimen netral, sehingga disarankan penggunaan teknik oversampling pada penelitian selanjutnya untuk menangani ketidak-seimbangan data.
Aplikasi Google Colab Berbasis Python dalam Menerapkan Teori Pohon dengan Algoritma Random Forest Classifier Dede Prabowo Wiguna; Lisda Juliana pangaribuan; Sakaria Efrata Ginting
Journal of Engineering and Applied Technology Vol 1 No 2 (2025): December: Scripta Technica: Journal of Engineering and Applied Technology
Publisher : CV SCRIPTA INTELEKTUAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65310/ybbpgv52

Abstract

This study examines the application of Python-based Google Colab in implementing tree theory through the Random Forest Classifier algorithm for income classification in data science, artificial intelligence, and machine learning professions. The research adopts an experimental quantitative approach using secondary data sourced from a global employment dataset. The methodological process includes data preprocessing, feature selection, class balancing, model training, and performance evaluation within the Google Colab environment. The results demonstrate that Random Forest effectively represents tree theory through ensemble decision structures capable of handling complex and heterogeneous data. Model evaluation indicates a satisfactory level of accuracy, confirming the classifier’s ability to generalize patterns across different income categories. Feature importance analysis reveals that job title, experience level, and company location play a significant role in determining income classification. These findings highlight the relevance of Random Forest as both a predictive and interpretative model, while emphasizing Google Colab’s effectiveness as a computational platform for machine learning experimentation. Overall, the study contributes to the practical understanding of tree-based algorithms and their application in analyzing labor market dynamics within the digital economy.    
Co-Authors Duma Lasmaria Siagian Fifin Sonata Fifin Sonata Ginting, Sakaria Efrata Hutagalung, Juniar Hutagalung, Juniar Jenheri Rejeki tarigan Kusnasari, Sri Kustini, Rini Lisda Juliana Pangaribuan Monang Tarigan Raldi Hendro Koestoer, Raldi Hendro Sakaria Efrata Ginting Sembiring, Lismardiana Sonata, Fifin - Tito Latif Indra Tulus Pramita Sihaloho