Sentiment Analysis and Topic Modelling Using the LDA Method related to the Flood Disaster in Jakarta on Twitter

Abstract

The widespread use of social media makes people tend to offer various information and opinions via Twitter. One of them is related to the flood disaster that occurred in Jakarta. This study aims to analyze the sentiment shown by the public when floods occur using a lexicon-based approach. Besides, this research also applies the topic modeling approached using the Latent Dirichlet Allocation (LDA) method to identify the topics discussed during the flood disaster. The results show that most opinions show negative sentiment with the topics discussed include information about the flooded areas, the impact of the flood disaster, conditions during the disaster, and feedback from the public to related parties of flood disaster management. The originality of this research lies in the use of the LDA method in modeling topics and analyzing sentiments related to the Jakarta flood disaster on social media.