Article Per Year (5 Year)
p-Index From 2021 - 2026
2.233
P-Index
This Author published in this journals
All Journal JSM (Jurnal SIFO Mikroskil) JURNAL MEDIA INFORMATIKA BUDIDARMA Indonesian Journal of Artificial Intelligence and Data Mining JMM (Jurnal Masyarakat Mandiri) Batoboh : Jurnal Pengabdian Pada Masyarakat JOURNAL OF SCIENCE AND SOCIAL RESEARCH REMIK : Riset dan E-Jurnal Manajemen Informatika Komputer Komatika: Jurnal Pengabdian Kepada Masyarakat Jurnal Masyarakat Indonesia
Nuraina Nuraina
Universitas Mikroskil
Arts Humanities 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 Social Sciences Other

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

Found 12 Documents
Search

 1   2 
PREDIKSI POLUSI UDARA BERDASARKAN TINGKAT CURAH HUJAN MENGGUNAKAN MODEL LSTM, BILSTM DAN PROPHET Nuraina Nuraina; Erwin Setiawan Panjaitan; Sofiana Nurjanah
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 8 No. 4 (2025): November 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i4.5764

Abstract

Abstract: The city of Jakarta, as the center of Indonesia's economic life and growth, continues to experience an astonishing population surge, reaching 11,248,839 people by 2024. However, this growth is inseparable from negative consequences, such as increased activity and modernization, which significantly affect air quality. Air pollution, as a direct impact of these changes, has exceeded national air quality standards, endangering human, animal, and plant health. Understanding the relationship between air pollution and weather conditions is crucial in determining future control measures. In this study, we used the LSTM, BiLSTM, and Prophet models on air pollution data. The results show that the single BiLSTM model and the BiLSTM-Prophet hybrid model provide the best performance, with accuracy levels reaching 99.32% and 99.31%, respectively. These findings provide a solid basis for forecasting and controlling potential future air pollution levels, as well as identifying key factors contributing to air quality in the capital city. . Keyword: Air Pollution, LSTM, BiLSTM, Prophet, Rainfall Abstrak: Kota Jakarta, sebagai pusat kehidupan dan pertumbuhan ekonomi Indonesia, terus mengalami lonjakan penduduk yang menakjubkan, mencapai 11.248.839 orang pada tahun 2024. Namun, pertumbuhan ini tidak terlepas dari konsekuensi negatif, seperti peningkatan aktivitas dan modernisasi, yang secara signifikan mempengaruhi kualitas udara. Polusi udara, sebagai dampak langsung dari perubahan ini, telah melampaui standar kualitas udara nasional, membahayakan kesehatan manusia, hewan, dan tumbuhan. Memahami hubungan antara polusi udara dan kondisi cuaca sangat penting dalam menentukan langkah-langkah pengendalian di masa depan. Dalam penelitian ini, kami menggunakan model LSTM, BiLSTM, dan Prophet pada data polusi udara. Hasil penelitian menunjukkan bahwa model tunggal BiLSTM dan model hybrid BiLSTM-Prophet memberikan kinerja terbaik, dengan tingkat akurasi masing-masing mencapai 99,32% dan 99,31%. Temuan ini memberikan dasar yang kuat untuk memperkirakan dan mengendalikan potensi tingkat polusi udara di masa depan, serta mengidentifikasi faktor-faktor kunci yang berkontribusi terhadap kualitas udara di ibu kota. Kata kunci: Polusi udara, LSTM, BiLSTM, Prophet, Curah hujan
INDOBERTWEET DENGAN TEMPORAL ATTENTION MECHANISM UNTUK DETEKSI ISU BENCANA DINAMIS MULTIPLATFORM Nurhayati; Tanti; Nuraina; Arisman; Felix
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 2 (2026): April 2026
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/qtam3c42

Abstract

Abstract: The development of disaster-related information in the digital space is very rapid and is often detected earlier through social media than through official government channels. This condition highlights the need for a system capable of detecting disaster-related issues quickly and dynamically across various digital platforms. This study aims to develop a dynamic disaster issue detection model based on IndoBERTweet with a Temporal Attention Mechanism using multiplatform big text data in Indonesia. The research methodology includes collecting textual data from various digital platforms such as Twitter, YouTube, TikTok, Quora, and Medium. The data are processed through preprocessing stages using Natural Language Processing (NLP) techniques, timestamp extraction to obtain temporal information, and the application of fine-grained labeling for more detailed classification of disaster-related issues. Subsequently, the IndoBERTweet model is trained with a Temporal Attention Mechanism to capture the relationship between textual context and temporal dynamics in the development of disaster-related issues. The expected results of this research are a model capable of dynamically detecting disaster-related issues by considering informal language contexts and temporal changes. This model is expected to support early warning systems and data-driven disaster management decision-making in Indonesia.   Keywords: Disaster Issue Detection; Social Media Text Analysis; Multiplatform Big Data; IndoBERTweet; Temporal Attention.   Abstrak: Perkembangan informasi kebencanaan di ruang digital berlangsung sangat cepat dan sering kali lebih dahulu terdeteksi melalui media sosial dibandingkan melalui kanal resmi pemerintah. Kondisi ini menunjukkan perlunya sistem yang mampu mendeteksi isu bencana secara cepat dan dinamis dari berbagai platform digital. Penelitian ini bertujuan mengembangkan model deteksi isu bencana dinamis berbasis IndoBERTweet dengan Temporal Attention Mechanism pada big data teks multiplatform di Indonesia. Metode penelitian meliputi pengumpulan data teks dari berbagai platform digital seperti Twitter, YouTube, TikTok, Quora, dan Medium. Data diproses melalui tahapan preprocessing menggunakan teknik Natural Language Processing (NLP), ekstraksi timestamp untuk memperoleh informasi temporal, serta penerapan fine-grained labeling untuk klasifikasi isu bencana yang lebih rinci. Selanjutnya, model IndoBERTweet dilatih dengan Temporal Attention Mechanism untuk menangkap hubungan antara konteks teks dan dinamika waktu dalam perkembangan isu bencana. Hasil penelitian diharapkan menghasilkan model yang mampu mendeteksi isu bencana secara dinamis dengan mempertimbangkan konteks bahasa informal dan perubahan waktu. Model ini diharapkan mendukung sistem peringatan dini dan pengambilan kebijakan kebencanaan berbasis data di Indonesia.   Kata kunci: Deteksi Isu Bencana; Analisis Teks Media Sosial; Big Data Multiplatform; IndoBERTweet; Temporal Attention.
Co-Authors Amanda Novita Soesetyo Angela Angela Apren Halomoan Hutasoit Arisman Calitos Liecardo Cindy Aprilia Cory Casuary Culita Dimas Arya Arjuna Djoni Djoni Erwin Setiawan Panjaitan Felix Felix Jenson Wijaya Hanes Hanes Isabell Isabell Joy Nasten Sinaga Kelvin Kelvin Kristian Telaumbanua Lina Lestari Marcella Corry Meela Tangkas Megawati Megawati Muhammad Refdi Pasaribu Murdiaty Murdiaty Nanda felani Baihaqi Nurhayati Nurhayati Nurhayati Ronsen Purba Salsabila, Zulpa Salsalina Br Sembiring Sarmauli Hanny Siagian Sofiana Nurjanah Suminar Ariwibowo Syahrial Sitorus Tanti Tri Wulandari Ginting Zulpa Salsabila