Selecting classification features for detection of mass emergencies on social media

Research output: Chapter in Book/Report/Conference proceedingConference contribution


External organisations

  • Georgia Tech Research Institute
  • University of Wisconsin


The paper addresses the problem of detecting eyewitness reports of mass emergencies on Twitter. This is the first work to conduct a large-scale comparative evaluation of classification features extracted from Twitter posts, using different learning algorithms and datasets representing a broad range of mass emergencies including both natural and technological disasters. We investigate the relative importance of different feature types as well as on the effect of several feature selection methods applied to this problem. Because the task of detecting mass emergencies is characterized by high heterogeneity of the data, our primary focus is on identifying those features that are capable of separating mass emergency reports from other messages, irrespective of the type of the disaster.


Original languageEnglish
Title of host publicationProceedings of the 2016 International Conference on Security and Management
Subtitle of host publicationSAM'16
Publication statusAccepted/In press - 10 May 2016
EventThe 2016 International Conference on Security and Management : (SAM'16) - Nevada, Las Vegas, United States
Duration: 25 Jul 201628 Jul 2016


ConferenceThe 2016 International Conference on Security and Management
CountryUnited States
CityLas Vegas


  • text classification, machine learning, feature selection, social media, social media analysis, disaster management