Unveiling Key Themes and Establishing a Hierarchical Taxonomy of Disaster-Related Tweets: A Text Mining Approach for Enhanced Emergency Management Planning

Abstract

Effectively harnessing the power of social media data for disaster management requires sophisticated analysis methods and frameworks. This research focuses on understanding the contextual information present in social media posts during disasters and developing a taxonomy to effectively categorize and classify the diverse range of topics discussed. First, the existing literature on social media analysis in disaster management is explored, highlighting the limitations and gaps in current methodologies. Second, a dataset comprising real-time social media posts related to various disasters is collected and preprocessed to ensure data quality and reliability. Third, three well-established topic modeling techniques, namely Latent Dirichlet Allocation (LDA), Latent Semantic Analysis (LSA), and Non-Negative Matrix Factorization (NMF), are employed to extract and analyze the latent topics and themes present in the social media data. The contributions of this research lie in the development of a taxonomy that effectively categorizes and classifies disaster-related social media data, the identification of key latent topics and themes, and the extraction of valuable insights to support and enhance emergency management efforts. Overall, the findings of this research have the potential to transform the way emergency management and response are conducted by harnessing the power of social media data. By incorporating these insights into decision-making processes, emergency managers can make more informed and strategic choices, resulting in more efficient and effective emergency response strategies. This, in turn, leads to improved outcomes, better utilization of resources, and ultimately, the ability to save lives and mitigate the impacts of disasters.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 7 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.