AIDR: Artificial intelligence for disaster response

Muhammad Imran, Carlos Castillo, Ji Lucas, Patrick Meier, Sarah Vieweg

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

453 Citations (Scopus)

Abstract

We present AIDR (Artificial Intelligence for Disaster Re- sponse), a platform designed to perform automatic classification of crisis-related microblog communications. AIDR enables humans and machines to work together to apply hu- man intelligence to large-scale data at high speed. The objective of AIDR is to classify messages that peo- ple post during disasters into a set of user-defined categories of information (e.g., \needs", \damage", etc.) For this pur- pose, the system continuously ingests data from Twitter, processes it (i.e., using machine learning classification tech- niques) and leverages human-participation (through crowd- sourcing) in real-time. AIDR has been successfully tested to classify informative vs. non-informative tweets posted dur- ing the 2013 Pakistan Earthquake. Overall, we achieved a classification quality (measured using AUC) of 80%. AIDR is available at http://aidr.qcri.org/.

Original languageEnglish
Title of host publicationWWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web
PublisherAssociation for Computing Machinery, Inc
Pages159-162
Number of pages4
ISBN (Electronic)9781450327459
DOIs
Publication statusPublished - 7 Apr 2014
Event23rd International Conference on World Wide Web, WWW 2014 - Seoul, Korea, Republic of
Duration: 7 Apr 201411 Apr 2014

Publication series

NameWWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web

Conference

Conference23rd International Conference on World Wide Web, WWW 2014
Country/TerritoryKorea, Republic of
CitySeoul
Period7/04/1411/04/14

Keywords

  • Classification
  • Crowdsourcing
  • Online machine learning
  • Stream processing

Fingerprint

Dive into the research topics of 'AIDR: Artificial intelligence for disaster response'. Together they form a unique fingerprint.

Cite this