Yonatan Yolius Anggara
Pendidikan Geografi S-2, Fakultas Ilmu Sosial, Universitas Negeri Yogyakarta, Indonesia

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

ANALISIS RESPON PUBLIK DAN PERMODELAN TOPIK MENGGUNAKAN LATENT DIRICHLET ALLOCATION METHOD (LDA) PADA BENCANA BANJIR BANDANG DI SUMATERA BARAT 2024 MELALUI TWITTER Yonatan Yolius Anggara; Nursida Arif
INDONESIAN JOURNAL OF ENVIRONMENT AND DISASTER Vol. 4 No. 1 (2025): Indonesian Journal of Environment and Disaster
Publisher : Disaster Research Center, Universitas Sebelas Maret, Surakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/h5qqjh18

Abstract

This study examines public sentiment during flash floods in West Sumatra by analyzing Twitter data using NLP through text2data.com. It employs the Latent Dirichlet Allocation (LDA) method for topic modeling to identify key discussion themes. The results reveal that 97.9% of expressed sentiments were positive, focusing on disaster impacts, situational conditions, causes of floods, and public responses to government actions in disaster management. The research highlights the role of social media in shaping public discourse during crises. Its novelty lies in combining LDA-based topic modeling with sentiment analysis specifically for flash flood-related discussions on Twitter in West Sumatra. This approach provides insights into how communities communicate and perceive natural disasters through digital platforms, offering potential applications for crisis communication strategies and policy improvements in disaster response. The findings demonstrate the predominance of constructive dialogue during environmental emergencies on social media.