Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jurnal ULTIMATICS Jurnal Teknologi
Gunawan Gunawan
Universitas Pancasakti Tegal
Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Deteksi Misinformasi dan Analisis Sentimen Konflik Israel–Iran pada Komentar YouTube Menggunakan Machine Learning dan Natural Language Processing Wresti Andriani; Gunawan Gunawan; Naella Nabila Putri Wahyuning N
Jurnal Teknologi Vol. 13 No. 2 (2026): Jurnal Teknologi
Publisher : Universitas Jayabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31479/jtek.v13i2.445

Abstract

Konflik Iran–Israel memunculkan diskusi publik di media sosial, termasuk komentar Youtube yang berpotensi mengandung misinformasi dan sentimen emosional. Penelitian ini bertujuan menganalisis deteksi misinformasi dan sentimen pada komentar Youtube terkait konflik Iran–Israel menggunakan pendekatan Machine Learning dan Natural Language Processing. Dataset penelitian terdiri atas 124 komentar publik Youtube berbahasa Indonesia yang dikumpulkan dari 12 video relevan. Data diproses melalui pembersihan, anonimisasi, dan pelabelan manual untuk dua tugas, yaitu deteksi misinformasi dan analisis sentimen. Representasi fitur menggunakan TF-IDF, sedangkan model klasifikasi yang dibandingkan meliputi Logistic Regression, Linear Support Vector Machine, dan Random Forest. Evaluasi dilakukan menggunakan accuracy, precision, recall, dan F1-score dengan stratified 5-fold cross-validation. Hasil penelitian menunjukkan bahwa Linear SVM memperoleh performa terbaik pada deteksi misinformasi dengan accuracy 0.7581 dan F1-score 0.2500. Pada analisis sentimen, Logistic Regression memperoleh performa terbaik dengan accuracy 0.7742 dan macro F1-score 0.4965. Namun, hasil masih dipengaruhi keterbatasan dataset dan ketidakseimbangan label, terutama dominasi kelas negative dan minimnya kelas neutral. Dengan demikian, penelitian ini merupakan baseline eksploratif awal dan belum dapat digeneralisasi secara luas terhadap seluruh opini publik digital pada isu konflik geopolitik serupa, sehingga perlu perluasan data dan model kontekstual lanjutan Keywords: konflik Iran–Israel, misinformation detection, machine learning, YouTube comments
Machine Learning for Chili Pepper Price Forecasting Using Exogenous Public-Attention Signals and Bayesian Hyperparameter Optimization Wresti Andriani; Gunawan Gunawan; Naella Nabila Putri Wahyuning Naja
ULTIMATICS Vol 18 No 1 (2026): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v18i1.4439

Abstract

Chili prices in Indonesia are highly volatile due to seasonal production, fragile supply chains, and shocks in public perception. This study improves short-run forecast accuracy by adding public-attention signals (Google Trends and news volume) as exogenous features summarized in a Shock Index. Evaluation metrics are sMAPE (primary), RMSE, and MASE; hyperparameters are tuned via Bayesian HPO. Empirically, the attention-augmented configuration (S4: +Trends +News +Shock) is best. Post-HPO (average across horizons), S4 attains sMAPE 12.47%, RMSE 3,433 IDR/kg, and MASE 0.87. By horizon, S4’s sMAPE is 9.8% (H=1), 12.0% (H=2), 15.6% (H=4); RMSE 2,550/3,350/4,400 IDR/kg; MASE 0.78/0.86/0.96. Compared with the price-only (S1) baseline, S4 is already better pre-tuning and becomes even stronger after HPO (average sMAPE reduction ≈ −6.2% relative). These findings show that incorporating the intensity of public issues enhances predictive value—especially at longer horizons when uncertainty rises—and that the approach is ready for operational use in nowcasting and early-warning.
Co-Authors Naella Nabila Putri Wahyuning N Naella Nabila Putri Wahyuning Naja Wresti Andriani