Abstract

The growing popularity of Twitter as an information medium has allowed unprecedented access to first-hand information during crises and mass emergency situations. Due to the sheer volume of information generated during a disaster, a key challenge is to filter tweets from the crisis region so their analysis can be prioritized. In this paper, we introduce the task of identifying whether a tweet is generated from crisis regions and formulate it as a decision problem. This problem is challenging due to the fact that only ∼1% of all tweets have location information. Existing approaches tackle this problem by predicting the location of the user using historical tweets from users or their social network. As collecting historical information is not practical during emergency situations, we investigate whether it is possible to determine that a tweet originates from the crisis region through the information in the tweet and the publishing user's profile.

Original languageEnglish (US)
Title of host publicationHT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media
PublisherAssociation for Computing Machinery
Pages255-260
Number of pages6
ISBN (Print)9781450329545
DOIs
StatePublished - 2014
Event25th ACM Conference on Hypertext and Social Media, HT 2014 - Santiago, Chile
Duration: Sep 1 2014Sep 4 2014

Other

Other25th ACM Conference on Hypertext and Social Media, HT 2014
CountryChile
CitySantiago
Period9/1/149/4/14

Fingerprint

Disasters

Keywords

  • crisis tweets
  • situational awareness
  • user behavior in tweets

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software

Cite this

Kumar, S., Hu, X., & Liu, H. (2014). A behavior analytics approach to identifying tweets from crisis regions. In HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media (pp. 255-260). Association for Computing Machinery. https://doi.org/10.1145/2631775.2631814

A behavior analytics approach to identifying tweets from crisis regions. / Kumar, Shamanth; Hu, Xia; Liu, Huan.

HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, 2014. p. 255-260.

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

Kumar, S, Hu, X & Liu, H 2014, A behavior analytics approach to identifying tweets from crisis regions. in HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, pp. 255-260, 25th ACM Conference on Hypertext and Social Media, HT 2014, Santiago, Chile, 9/1/14. https://doi.org/10.1145/2631775.2631814
Kumar S, Hu X, Liu H. A behavior analytics approach to identifying tweets from crisis regions. In HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media. Association for Computing Machinery. 2014. p. 255-260 https://doi.org/10.1145/2631775.2631814
Kumar, Shamanth ; Hu, Xia ; Liu, Huan. / A behavior analytics approach to identifying tweets from crisis regions. HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, 2014. pp. 255-260
@inproceedings{f7c76d33d7f94f1f8be91405d9a67c4b,
title = "A behavior analytics approach to identifying tweets from crisis regions",
abstract = "The growing popularity of Twitter as an information medium has allowed unprecedented access to first-hand information during crises and mass emergency situations. Due to the sheer volume of information generated during a disaster, a key challenge is to filter tweets from the crisis region so their analysis can be prioritized. In this paper, we introduce the task of identifying whether a tweet is generated from crisis regions and formulate it as a decision problem. This problem is challenging due to the fact that only ∼1{\%} of all tweets have location information. Existing approaches tackle this problem by predicting the location of the user using historical tweets from users or their social network. As collecting historical information is not practical during emergency situations, we investigate whether it is possible to determine that a tweet originates from the crisis region through the information in the tweet and the publishing user's profile.",
keywords = "crisis tweets, situational awareness, user behavior in tweets",
author = "Shamanth Kumar and Xia Hu and Huan Liu",
year = "2014",
doi = "10.1145/2631775.2631814",
language = "English (US)",
isbn = "9781450329545",
pages = "255--260",
booktitle = "HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - A behavior analytics approach to identifying tweets from crisis regions

AU - Kumar, Shamanth

AU - Hu, Xia

AU - Liu, Huan

PY - 2014

Y1 - 2014

N2 - The growing popularity of Twitter as an information medium has allowed unprecedented access to first-hand information during crises and mass emergency situations. Due to the sheer volume of information generated during a disaster, a key challenge is to filter tweets from the crisis region so their analysis can be prioritized. In this paper, we introduce the task of identifying whether a tweet is generated from crisis regions and formulate it as a decision problem. This problem is challenging due to the fact that only ∼1% of all tweets have location information. Existing approaches tackle this problem by predicting the location of the user using historical tweets from users or their social network. As collecting historical information is not practical during emergency situations, we investigate whether it is possible to determine that a tweet originates from the crisis region through the information in the tweet and the publishing user's profile.

AB - The growing popularity of Twitter as an information medium has allowed unprecedented access to first-hand information during crises and mass emergency situations. Due to the sheer volume of information generated during a disaster, a key challenge is to filter tweets from the crisis region so their analysis can be prioritized. In this paper, we introduce the task of identifying whether a tweet is generated from crisis regions and formulate it as a decision problem. This problem is challenging due to the fact that only ∼1% of all tweets have location information. Existing approaches tackle this problem by predicting the location of the user using historical tweets from users or their social network. As collecting historical information is not practical during emergency situations, we investigate whether it is possible to determine that a tweet originates from the crisis region through the information in the tweet and the publishing user's profile.

KW - crisis tweets

KW - situational awareness

KW - user behavior in tweets

UR - http://www.scopus.com/inward/record.url?scp=84907409170&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907409170&partnerID=8YFLogxK

U2 - 10.1145/2631775.2631814

DO - 10.1145/2631775.2631814

M3 - Conference contribution

AN - SCOPUS:84907409170

SN - 9781450329545

SP - 255

EP - 260

BT - HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media

PB - Association for Computing Machinery

ER -