Modeling Climate Change Issues in Indonesia Based on Media Headlines

Abstract

Climate change has become a global issue affecting all countries in the last decades. This phenomenon poses a concern to Indonesia as it is one of the climate change’s epicenters. Various studies have shown that climate change can harm multiple community activities, such as unstable agricultural production, decreased people’s health, and global warming. This study tried to model and analyze climate change topics discussed in the media. Finding hidden topics from texts can provide clues and information regarding public conversation surrounding climate change, such as public thoughts, perceptions, and readiness to mitigate the possible adverse effects of climate change. In order to identify hidden subjects from the corpus, this work modeled climate change issues in Indonesia using the latent Dirichlet allocation (LDA) algorithm to analyze texts from Indonesian media headlines. As many as 7,000 headline data from five online media were collected from 2017 to 2021 using web scraping techniques. The proposed approach produced eight topics related to climate change, which were determined by the highest coherence value of 0.560. Those topics were renewable energy, carbon emissions, environmental management, development economics, international cooperation, policy/regulation, rehabilitation, and disaster. Based on the results, the model could sufficiently describe the theme of discussion in society and photograph public thoughts and the government’s readiness in the form of policies and regulations in dealing with the climate change phenomenon.

Keywords

• climate change
• lda
• text analysis
• text mining
• topic modeling