IMPLEMENTASI LSTM UNTUK ANALISIS SENTIMEN PERSEPSI MASYARAKAT TERHADAP BANJIR SUMATERA 2025 DI YOUTUBE
DOI:
https://doi.org/10.36002/jutik.v12i1.5212Keywords:
Disaster analysis, Long Short-Term Memory, sentiment analysis, social media mining, youtube commentsAbstract
Sumatra Flash Flood triggered extensive public discussion on social media regarding the causes of the disaster, particularly between natural factors and human factors. Understanding public perception is important for evaluating disaster literacy and mitigation communication strategies. This study analyzes public perceptions of the disaster’s causes using sentiment analysis based on the Long Short-Term Memory (LSTM) algorithm applied to YouTube comments. A total of 15,259 comments were collected using the YouTube Data API and processed through data cleaning and lexicon-based automatic labeling. After data selection, 11,043 comments were used for model training and testing. The experimental results show that the LSTM model achieved an accuracy of 96.29% and a ROC-AUC value of 0.99. Sentiment distribution analysis indicates that 57% of comments emphasize human factors, while 43% highlight natural factors or religious interpretations. These findings suggest an increasing public awareness of the human role in disaster risk and demonstrate the effectiveness of LSTM for Indonesian-language disaster sentiment analysis.
References
[1] Maruli, “TRAGEDI SUMATRA 2025 — ‘Banjir Neraka Sumatra Pecah Rekor: Korban Lewat 700 Jiwa, 1 Juta Warga Mengungsi, Negara Dikepung Krisis!,’” Gakorpan News. [Daring]. Tersedia pada: https://www.gakorpan.com/tragedi-sumatra-2025-banjir-neraka-sumatra-pecah-rekor-korban-lewat-700-jiwa-1-juta-warga-mengungsi-negara-dikepung-krisis
[2] Matius Alfons Hutajulu, “Korban Tewas Bencana Sumatera Capai 1.006 Orang, 217 Masih Hilang”, detikNews. [Daring]. Tersedia pada: https://news.detik.com/berita/d-8258300/korban-tewas-bencana-sumatera-capai-1-006-orang-217-masih-hilang
[3] Agungnoe, “Bencana Banjir Bandang Sumatra, Pakar UGM Sebut Akibat Kerusakan Ekosistem Hutan di Hulu DAS,” Universitas Gadjah Mada. [Daring]. Tersedia pada: https://ugm.ac.id/id/berita/bencana-banjir-bandang-sumatra-pakar-ugm-sebut-akibat-kerusakan-ekosistem-hutan-di-hulu-das/
[4] SINDONews, “Ketua BNPB Dikecam Publik Usai Pernyataan soal Banjir Sumatra Dianggap ‘Gaduh Medsos’ | The Comment,” 2025. [Daring]. Tersedia pada: https://www.youtube.com/watch?v=HKix6SrVxGM.
[5] Kompas.com, “Pakar ITB Ungkap Penyebab Banjir Sumatera, Termasuk Hilangnya Resapan,” Youtube, 2025. [Daring]. Tersedia pada: https://www.youtube.com/watch?v=tfJC0bn9gHs
[6] Narasi, “Meliput Banjir Sumatera: Air Masih Tinggi, Jalan Terputus | Mata Najwa,” Mata Najwa, 2025. [Daring]. Tersedia pada: https://www.youtube.com/watch?v=ouR11bOMzVM
[7] B. Ilyas dan A. Sharifi, “A systematic review of social media-based sentiment analysis in disaster risk management,” Int. J. Disaster Risk Reduct., vol. 123, hlm. 105487, Jun 2025, doi: 10.1016/j.ijdrr.2025.105487.
[8] D. Contreras, S. Wilkinson, E. Alterman, dan J. Hervás, “Accuracy of a pre-trained sentiment analysis (SA) classification model on tweets related to emergency response and early recovery assessment: the case of 2019 Albanian earthquake,” Nat. Hazards, vol. 113, no. 1, hlm. 403–421, Agu 2022, doi: 10.1007/s11069-022-05307-w.
[9] C. Hu, A. Peters, dan D. Kang, “LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data,” Proc. VLDB Endow., vol. 18, no. 2, hlm. 253–264, Okt 2024, doi: 10.14778/3705829.3705843.
[10] J. Khan, K. Ahmad, S. K. Jagatheesaperumal, dan K.-A. Sohn, “Textual variations in social media text processing applications: challenges, solutions, and trends,” Artif. Intell. Rev., vol. 58, no. 3, hlm. 89, Jan 2025, doi: 10.1007/s10462-024-11071-z.
[11] B. Omarov dan Z. Zhumanov, “Bidirectional Long-Short-Term Memory with Attention Mechanism for Emotion Analysis in Textual Content,” Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 6, 2023, doi: 10.14569/IJACSA.2023.0140615.
[12] X. Chen, “Monitoring of Public Opinion on Typhoon Disaster Using Improved Clustering Model Based on Single-Pass Approach,” Sage Open, vol. 13, no. 3, hlm. 21582440231200098, Jul 2023, doi: 10.1177/21582440231200098.
[13] B. Wan, P. Wu, C. K. Yeo, dan G. Li, “Emotion-cognitive reasoning integrated BERT for sentiment analysis of online public opinions on emergencies,” Inf. Process. Manag., vol. 61, no. 2, hlm. 103609, Mar 2024, doi: 10.1016/j.ipm.2023.103609.
[14] M. H. Fardana, W. S. J. Saputra, dan M. H. P. Swari, “Analysis And Prediction Of Motor Vehicle Carbon Dioxide Emissions Using A Hybrid Lstm And Arima Algorithm,” J. Inform. Dan Tek. Elektro Terap., vol. 13, no. 3, Jul 2025, doi: 10.23960/jitet.v13i3.6782.
[15] K. L. Tan, C. P. Lee, dan K. M. Lim, “A Survey of Sentiment Analysis: Approaches, Datasets, and Future Research,” Appl. Sci., vol. 13, no. 7, hlm. 4550, Apr 2023, doi: 10.3390/app13074550.
[16] I. P. Ramayasa, I. G. A. D. Saryanti, I. K. Dharmendra, and Edwar, “Perbandingan Metode Vektorisasi Pada Analisa Sentiment, Studi Kasus: Cyberbullying Pada Komentar Instagram,” Jurnal Teknologi Informasi dan Komputer, vol. 9, no. 5, pp. 505-512, Oct. 2023, doi: https://doi.org/10.36002/jutik.v9i5.2645.
[17] I. G. B. Arinata, I. P. Satwika, and N. W. Utami, "Analisis Sentimen Pada EDOM STMIK Primakara Menggunakan Metode Long Short-Term Memory," Jurnal Teknologi Informasi dan Komputer, vol. 8, no. 4, pp. 327-332, Oct. 2022, doi: https://doi.org/10.36002/jutik.v8i4.2086.
[18] F. E. L. Otto dan E. Raju, “Harbingers of decades of unnatural disasters,” Commun. Earth Environ., vol. 4, no. 1, hlm. 280, Agu 2023, doi: 10.1038/s43247-023-00943-x.
[19] D. Marks dan I. G. Baird, “The urban political ecology of worsening flooding in Phnom Penh, Cambodia: Neopatrimonialism, displacement, and uneven harm,” Int. J. Disaster Risk Reduct., vol. 118, hlm. 105229, Feb 2025, doi: 10.1016/j.ijdrr.2025.105229.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 JUTIK : Jurnal Teknologi Informasi dan Komputer
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
