Claim Missing Document
Check
Articles

Found 2 Documents
Search

Analisis Sentimen Air Mineral dan Demineral Menggunakan SVM pada Dataset Tidak Seimbang Rana, Dipo Yudhis; Fadillah, Nur; Syarifah, Asyifa Raudha; Afiandri, Dhea Aulia; Rianto, Harsih; Nuryamin, Yamin; Susilowati, Susi
Journal Automation Computer Information System Vol. 5 No. 2 (2025): November
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/jacis.v5i2.138

Abstract

Penelitian ini menganalisis sentimen opini pengguna platform X terhadap air mineral dan air demineral menggunakan pendekatan kuantitatif eksperimental. Data set terdiri dari 140 tweet yang dilabeli manual ke dalam tiga kategori: positif (38.57%), negatif (13.57%), dan netral (47.86%). Ketidakseimbangan kelas ekstrem dan ukuran data set yang sangat kecil menjadi tantangan utama yang mendasari novelty penelitian ini. Penelitian ini menguji hipotesis bahwa class weighting lebih efektif daripada Synthetic Minority Over-sampling Technique (SMOTE) pada dataset kecil. Klasifikasi menggunakan Support Vector Machine (SVM) dengan pra-pemrosesan teks (case folding, data cleaning, stemming Sastrawi, stopword removal) dan ekstraksi fitur Term Frequency-Inverse Document Frequency (TF-IDF). Evaluasi melalui 10-fold stratified cross-validation menunjukkan SVM dengan class weighting mencapai akurasi 57.14% dan F1-score macro 42.36%, sedikit mengungguli SMOTE (53.57% akurasi, 40.98% F1 macro). Uji statistik (Cohen's d = 0.125) mengkonfirmasi tidak ada perbedaan signifikan, membuktikan SMOTE tidak efektif pada dataset sangat kecil. Kelas minoritas (negatif) mencapai F1-score hanya 8%, menunjukkan tantangan ketidakseimbangan ekstrem. Kontribusi utama penelitian ini adalah validasi empiris bahwa class weighting lebih robust daripada SMOTE untuk analisis sentimen berbahasa Indonesia pada kondisi data terbatas
Optimalisasi Aplikasi E-Learning Berbasis Moodle Untuk Pengembangan Dan Peningkatan Media Pembelajaran Secara Digital Budi, Eko Setia; Priyatna, Ade; Zuraidah, Eva; Fadillah, Nur; Firmansyah, Ilhan; Rana, Dipo Yudhis; Fitriyani, Fitriyani; Roris, Renaldi Putra
JPM: Jurnal Pengabdian Masyarakat Vol. 6 No. 3 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jpm.v6i3.2751

Abstract

Community Service is a routine activity carried out by lecturers of Higher Education in order to carry out the obligations of the Tridharma of Higher Education. Lecturers have an obligation to carry out the obligation to share knowledge and skills they have with the wider community who need help. One of the partners who needs support is Al Qomar School which currently has problems in the information system in the digital learning process. This often causes errors in the digital learning process. In addition, the partner also does not have a website application that can be used to display the school's digital learning that makes it easier for teachers to access digital learning quickly and efficiently. Based on this, this community service aims to provide Moodle-Based E-Learning Application Training for the Development and Improvement of Digital Learning Media at Al Qomar School that can be used by partners to improve learning performance better. The activity was carried out face-to-face at the Al Qomar School Hall, Jalan Kamal Raya No. 1 Kalideres, West Jakarta. The target output to be achieved in this activity is the publication of this training activity in national-scale electronic or print media. Improving the ability of the e-learning system aims to provide effective solutions in increasing learning flexibility, accommodating diverse learning styles, and facilitating learning accessibility. E-learning development using the Moodle platform, 100% of teachers are able to design learning with creative and innovative content