Skip to main content
Article
CrisisLex: A Lexicon for Collecting and Filtering Microblogged Communications in Crises
Proceedings of ICWSM (2014)
  • Alexandra Olteanu, Ecole Polytechnique Federale de Lausanne
  • Carlos Castillo, Qatar Computing Research Institute
  • Fernando Diaz
  • Sarah Vieweg, Qatar Computing Research Institute
Abstract
Locating timely, useful information during crises and mass emergencies is critical for those forced to make potentially life-altering decisions. As the use of Twit- ter to broadcast useful information during such situa- tions becomes more widespread, the problem of find- ing it becomes more difficult. We describe an approach toward improving the recall in the sampling of Twit- ter communications that can lead to greater situational awareness during crisis situations. First, we create a lex- icon of crisis-related terms that frequently appear in rel- evant messages posted during different types of crisis situations. Next, we demonstrate how we use the lexi- con to automatically identify new terms that describe a given crisis. Finally, we explain how to efficiently query Twitter to extract crisis-related messages during emer- gency events. In our experiments, using a crisis lexi- con leads to substantial improvements in terms of recall when added to a set of crisis-specific keywords man- ually chosen by experts; it also helps to preserve the original distribution of message types.
Publication Date
2014
Citation Information
Alexandra Olteanu, Carlos Castillo, Fernando Diaz and Sarah Vieweg. "CrisisLex: A Lexicon for Collecting and Filtering Microblogged Communications in Crises" Proceedings of ICWSM (2014)
Available at: http://works.bepress.com/vieweg/16/