Article Per Year (5 Year)
p-Index From 2021 - 2026
2.133
P-Index
This Author published in this journals
All Journal Jurnal Informatika Kaputama (JIK) JTIK (Jurnal Teknik Informatika Kaputama) JUKI : Jurnal Komputer dan Informatika Journal of Artificial Intelligence and Engineering Applications (JAIEA) Jurnal Inovasi Ekonomi Syariah dan Akuntansi Repeater: Publikasi Teknik Informatika dan Jaringan Merkurius: Jurnal Riset Sistem Informasi dan Teknik Informatika Saturnus: Jurnal Teknologi dan Sistem Informasi Pascal: Journal of Computer Science and Informatics
Khadapi, Muammar
STMIK KAPUTAMA
Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Library & Information Science Social Sciences

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

Found 12 Documents
Search

 1   2 
Sentiment Analysis on the Failure of the Indonesian National Team to the 2026 World Cup During Patrick Kluivert's Coaching Period using the Support Vector Machine (SVM) Algorithm Ade Dharma; A M H Pardede; Muammar Khadapi
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 5 No. 3 (2026): June 2026
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v5i3.2353

Abstract

This study aims to analyze public sentiment regarding the failure of the Indonesian National Team to qualify for the 2026 FIFA World Cup during Patrick Kluivert’s coaching period using the Support Vector Machine (SVM) algorithm. Data were collected through web scraping from Twitter (X), YouTube, and Detik.com, resulting in 5,060 comments. The collected data were processed using Natural Language Processing (NLP), including case folding, cleaning, tokenization, stopword removal, normalization, and stemming. The labeled data were transformed using the Term Frequency–Inverse Document Frequency (TF-IDF) method and divided into training and testing sets with an 80:20 ratio. The classification model was developed using a linear kernel SVM and implemented through a Streamlit-based web application for interactive sentiment prediction. The results showed that negative sentiment dominated with 55.0%, followed by positive sentiment at 36.4% and neutral sentiment at 8.6%. Model evaluation achieved an accuracy of 78.44%, precision of 78.54%, recall of 78.44%, and f1-score of 78.48%. These findings indicate that the SVM method is effective in classifying public sentiment toward the performance of the Indonesian National Team.
MENAKAR ETIKA BERMEDIA SOSIAL SISWA SMP: SINERGI PENDIDIKAN KEWARGANEGARAAN DAN ILMU KOMPUTER DALAM ANALISIS DATA DIGITAL Khadapi, Muammar; Hafizhah Hamim Nasution
JTIK (Jurnal Teknik Informatika Kaputama) Vol. 10 No. 2 (2026): Artificial Intelligence (AI)
Publisher : STMIK KAPUTAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59697/jtik.v10i2.1395

Abstract

Perkembangan media sosial telah menggeser ruang interaksi siswa sekolah menengah dari lingkungan fisik menuju ruang digital yang minim pengawasan langsung, memunculkan berbagai polemik etika bermedia sosial di kalangan pelajar. Penelitian ini bertujuan mengintegrasikan pendekatan Pendidikan Kewarganegaraan dan Ilmu Komputer dalam menganalisis etika bermedia sosial siswa sekolah menengah melalui text mining terhadap komentar YouTube. Penelitian menggunakan desain deskriptif-kuantitatif berbasis data mining, dengan data berupa 778 komentar (406 dari YouTube Shorts, 372 dari video reguler) yang dikumpulkan melalui web scraping menggunakan Python di Google Colab dari tiga video pemberitaan kasus etika siswa sekolah menengah yang viral di media sosial. Data dianalisis melalui tahapan preprocessing (Sastrawi), analisis sentimen berbasis InSet Lexicon, kategorisasi rubrik etika digital berbasis kata kunci, dan topic modeling (LDA). Hasil penelitian menunjukkan dominasi sentimen negatif (80,7%), dengan kategori etika terbanyak berupa Penilaian Moral/Karakter (30,0%) dan Tuntutan Sanksi/Hukuman (23,4%). Topic modeling mengungkap tiga tema dominan: adab anak dan peran orang tua/sekolah (45,6%), kritik antargenerasi terhadap sikap siswa (20,0%), serta tuntutan sanksi tegas (34,4%). Penelitian juga membandingkan rubrik kata kunci dengan pendekatan zero-shot classification, yang menunjukkan bahwa keduanya masih memiliki keterbatasan saling melengkapi. Penelitian ini berkontribusi metodologis bagi riset Pendidikan Kewarganegaraan berbasis data digital, serta merekomendasikan penguatan literasi digital dan pendekatan restoratif dalam pembinaan karakter siswa.
Co-Authors Ade Dharma Amysa Putri Sitepu Arey Slaiman Arriza Khana Assya Harnita Lubis Astrid Noviriandini Buaton, Relita Hafizhah Hamim Nasution Herdina Putri Ahmadi Khair, Husnul Kurniawati Kurniawati Magdalena Simanjuntak Misjelina Br Surbakti Muhammad Arif Ridho Mujib Al Fathan Novriyenni Novriyenni Novriyenni, Novriyenni Pakpahan, Victor Maruli Pardede, Akim Manaor Hara Puspita Sari, Melani Roni Andarsyah Silvia Amara Simanjuntak, Magdalena Siti Lestari Sob Ey Soppry