Early detection of heterogeneous disaster events using social media

Viktor Pekar, Jane Binner, Hossein Najafi, Christopher Hale, Vincent A. Schmidt

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)
262 Downloads (Pure)

Abstract

This article addresses the problem of detecting crisis-related messages on social media, in order to improve the situational awareness of emergency services. Previous work focused on developing machine-learning classifiers restricted to specific disasters, such as storms or wildfires. We investigate for the first time methods to detect such messages where the type of the crisis is not known in advance, that is, the data are highly heterogeneous. Data heterogeneity causes significant difficulties for learning algorithms to generalize and accurately label incoming data. Our main contributions are as follows. First, we evaluate the extent of this problem in the context of disaster management, finding that the performance of traditional learners drops by up to 40% when trained and tested on heterogeneous data vis-á-vis homogeneous data. Then, in order to overcome data heterogeneity, we propose a new ensemble learning method, and found this to perform on a par with the Gradient Boosting and AdaBoost ensemble learners. The methods are studied on a benchmark data set comprising 26 disaster events and four classification problems: detection of relevant messages, informative messages, eyewitness reports, and topical classification of messages. Finally, in a case study, we evaluate the proposed methods on a real-world data set to assess its practical value.

Original languageEnglish
Pages (from-to)43-54
Number of pages12
JournalJournal of the Association for Information Science and Technology
Volume71
Issue number1
Early online date22 Mar 2019
DOIs
Publication statusPublished - Jan 2020

Keywords

  • Machine Learning
  • Semi-supervised learning
  • Ensemble classification
  • situational awareness

Fingerprint

Dive into the research topics of 'Early detection of heterogeneous disaster events using social media'. Together they form a unique fingerprint.

Cite this