Article Per Year (5 Year)
p-Index From 2021 - 2026
1.99
P-Index
This Author published in this journals
All Journal SITEKIN: Jurnal Sains, Teknologi dan Industri Jurnal Pendidikan Islam Iqra' IKRA-ITH EKONOMIKA Jurnal Kreativitas PKM Jurnal Teknik Informatika (JUTIF) Journal La Multiapp Indonesian Journal of Innovation Studies Jurnal Locus Penelitian dan Pengabdian Jurnal Sains Informatika Terapan (JSIT) Innovative: Journal Of Social Science Research Academia Open
Hasibuan, Alfiansyah
Unknown Affiliation
Aerospace Engineering Humanities Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Health Professions Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Mathematics Medicine & Pharmacology Nursing Public Health Other

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

Found 12 Documents
Search

 1   2 
Analisis Efektivitas Sistem Rekomendasi Berbasis Random Forest untuk Edukasi Rehabilitasi Narkoba di Masyarakat Kota Manado Silaarta, Hezeki Farell; Hasibuan, Alfiansyah; Kumajas, Sondy C.
Jurnal Locus Penelitian dan Pengabdian Vol. 5 No. 4 (2026): JURNAL LOCUS: Penelitian dan Pengabdian
Publisher : Riviera Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58344/locus.v5i4.5701

Abstract

Penyalahgunaan narkoba di Kota Manado menunjukkan tren peningkatan yang signifikan dan menjadi tantangan serius bagi upaya pencegahan serta edukasi rehabilitasi. Penelitian ini bertujuan menganalisis efektivitas sistem rekomendasi materi edukasi rehabilitasi berbasis algoritma Random Forest, yang dirancang untuk menyajikan konten pembelajaran terpersonalisasi sesuai karakteristik pengguna. Metode yang digunakan adalah Research and Development (R&D) dengan desain quasi-experimental melalui pretest-posttest control group design. Sampel penelitian terdiri atas 181 responden, terbagi dalam kelompok eksperimen (91 orang) dan kontrol (90 orang). Sistem dikembangkan menggunakan Python, Flask, dan PostgreSQL, dengan Random Forest sebagai algoritma klasifikasi berdasarkan variabel usia, jenis kelamin, minat edukasi, pekerjaan, dan skor pre-test. Hasil pengujian menunjukkan bahwa model Random Forest memiliki kinerja klasifikasi yang sangat tinggi, dengan akurasi, precision, recall, dan F1-score masing-masing mencapai 100%. Namun, uji efektivitas sistem memperlihatkan tidak adanya perbedaan signifikan antara kelompok eksperimen dan kontrol, baik pada nilai post-test (p = 0,3023) maupun gain score (p = 0,7503). Meskipun demikian, secara deskriptif kelompok eksperimen menunjukkan kecenderungan peningkatan skor lebih tinggi dibandingkan kelompok kontrol. Temuan ini mengindikasikan bahwa meskipun sistem rekomendasi bekerja optimal secara teknis, dampak intervensi terhadap peningkatan pemahaman belum signifikan secara statistik. Penelitian ini berkontribusi pada pengembangan sistem edukasi digital berbasis machine learning di bidang rehabilitasi narkoba, serta membuka peluang perbaikan melalui penambahan variabel prediktor, pengayaan level materi, dan perbandingan dengan algoritma lain pada penelitian selanjutnya.
Danantara YouTube Sentiment Shows Public Transparency Concerns: Sentimen YouTube Danantara Menunjukkan Kekhawatiran Transparansi Publik Wahani, Waraney Vincent Beckham; Hasibuan, Alfiansyah; Tinambunan, Medi Hermanto
Academia Open Vol. 11 No. 1 (2026): June
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/acopen.11.2026.14210

Abstract

General Background Social media comments offer valuable data for analyzing public discourse on policy issues. Specific Background This study investigates YouTube comments about Danantara, Indonesia's strategic investment body, using Natural Language Processing with 7,294 comments. Knowledge Gap Previous studies often analyze sentiment and topics separately, without integrated analysis or iterative labeling. Aims The study aims to classify sentiment using Support Vector Machine (SVM) and identify topics with Latent Dirichlet Allocation (LDA). Results 74.9% accuracy was achieved with SVM, classifying 58.0% of comments as negative, 29.3% neutral, and 12.8% positive. LDA revealed 6 topics for neutral, 4 for positive, and 3 for negative sentiment, with key concerns about transparency and corruption. Novelty This study integrates SVM and LDA with Human in the Loop labeling to capture both sentiment and topic substance. Implications Findings offer insights for improving transparency and public communication, while contributing to text mining in digital discourse. Highlights • The classifier achieved 74.9% accuracy after Human in the Loop labeling and manual verification.• Unfavorable polarity reached 58.0%, followed by neutral at 29.3% and positive at 12.8%.• Coherence scores selected 6 neutral, 4 positive, and 3 critical thematic clusters. Keywords Danantara; Sentiment Analysis; Topic Modeling; Support Vector Machine; Latent Dirichlet Allocation  
Co-Authors Djami Olii Gladly Caren Rorimpandey Keith Francis Ratumbuisang Kolauw, Evan Kumajas, Sondy C Kumajas, Sondy C. Kumajas, Sondy Campvid Kumowal, Jaklin Agnes Liow, Merlin Aprilia Mantik, Felitia Theona Geofani Marpaung, Effenril Agung Merriam Listiany Modeong Mokoginta, Fadlia Mustapa Mustapa Musung, Matthew Albert Alexander Putra, Purwa Hasan Quido Conferti Kainde Silaarta, Hezeki Farell Tinambunan, Medi Hermanto Wahani, Waraney Vincent Beckham