Tweet4act

Using incident-specific profiles for classifying crisis-related messages

Soudip Roy Chowdhury, Muhammad Imran, Muhammad Rizwan Asghar, Sihem Amer-Yahia, Carlos Castillo

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

39 Citations (Scopus)

Abstract

We present Tweet4act, a system to detect and classify crisis-related messages communicated over a microblogging platform. Our system relies on extracting content features from each message. These features and the use of an incident-specific dictionary allow us to determine the period type of an incident that each message belongs to. The period types are: Pre-incident (messages talking about prevention, mitigation, and preparedness), during-incident (messages sent while the incident is taking place), and post-incident (messages related to the response, recovery, and reconstruction). We show that our detection method can effectively identify incident-related messages with high precision and recall, and that our incident-period classification method outperforms standard machine learning classification methods.

Original languageEnglish
Title of host publicationISCRAM 2013 Conference Proceedings - 10th International Conference on Information Systems for Crisis Response and Management
PublisherKarlsruher Institut fur Technologie (KIT)
Pages834-839
Number of pages6
ISBN (Print)9783923704804
Publication statusPublished - 1 Jan 2013
Externally publishedYes
Event10th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2013 - Baden-Baden, Germany
Duration: 12 May 201315 May 2013

Other

Other10th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2013
CountryGermany
CityBaden-Baden
Period12/5/1315/5/13

Fingerprint

Glossaries
Learning systems
Recovery

Keywords

  • Crisis informatics
  • Disaster management
  • Microblogging
  • Twitter data-analytics

ASJC Scopus subject areas

  • Information Systems

Cite this

Chowdhury, S. R., Imran, M., Asghar, M. R., Amer-Yahia, S., & Castillo, C. (2013). Tweet4act: Using incident-specific profiles for classifying crisis-related messages. In ISCRAM 2013 Conference Proceedings - 10th International Conference on Information Systems for Crisis Response and Management (pp. 834-839). Karlsruher Institut fur Technologie (KIT).

Tweet4act : Using incident-specific profiles for classifying crisis-related messages. / Chowdhury, Soudip Roy; Imran, Muhammad; Asghar, Muhammad Rizwan; Amer-Yahia, Sihem; Castillo, Carlos.

ISCRAM 2013 Conference Proceedings - 10th International Conference on Information Systems for Crisis Response and Management. Karlsruher Institut fur Technologie (KIT), 2013. p. 834-839.

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

Chowdhury, SR, Imran, M, Asghar, MR, Amer-Yahia, S & Castillo, C 2013, Tweet4act: Using incident-specific profiles for classifying crisis-related messages. in ISCRAM 2013 Conference Proceedings - 10th International Conference on Information Systems for Crisis Response and Management. Karlsruher Institut fur Technologie (KIT), pp. 834-839, 10th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2013, Baden-Baden, Germany, 12/5/13.
Chowdhury SR, Imran M, Asghar MR, Amer-Yahia S, Castillo C. Tweet4act: Using incident-specific profiles for classifying crisis-related messages. In ISCRAM 2013 Conference Proceedings - 10th International Conference on Information Systems for Crisis Response and Management. Karlsruher Institut fur Technologie (KIT). 2013. p. 834-839
Chowdhury, Soudip Roy ; Imran, Muhammad ; Asghar, Muhammad Rizwan ; Amer-Yahia, Sihem ; Castillo, Carlos. / Tweet4act : Using incident-specific profiles for classifying crisis-related messages. ISCRAM 2013 Conference Proceedings - 10th International Conference on Information Systems for Crisis Response and Management. Karlsruher Institut fur Technologie (KIT), 2013. pp. 834-839
@inproceedings{3f7c89e688d946719d5402df4bb5a6bd,
title = "Tweet4act: Using incident-specific profiles for classifying crisis-related messages",
abstract = "We present Tweet4act, a system to detect and classify crisis-related messages communicated over a microblogging platform. Our system relies on extracting content features from each message. These features and the use of an incident-specific dictionary allow us to determine the period type of an incident that each message belongs to. The period types are: Pre-incident (messages talking about prevention, mitigation, and preparedness), during-incident (messages sent while the incident is taking place), and post-incident (messages related to the response, recovery, and reconstruction). We show that our detection method can effectively identify incident-related messages with high precision and recall, and that our incident-period classification method outperforms standard machine learning classification methods.",
keywords = "Crisis informatics, Disaster management, Microblogging, Twitter data-analytics",
author = "Chowdhury, {Soudip Roy} and Muhammad Imran and Asghar, {Muhammad Rizwan} and Sihem Amer-Yahia and Carlos Castillo",
year = "2013",
month = "1",
day = "1",
language = "English",
isbn = "9783923704804",
pages = "834--839",
booktitle = "ISCRAM 2013 Conference Proceedings - 10th International Conference on Information Systems for Crisis Response and Management",
publisher = "Karlsruher Institut fur Technologie (KIT)",

}

TY - GEN

T1 - Tweet4act

T2 - Using incident-specific profiles for classifying crisis-related messages

AU - Chowdhury, Soudip Roy

AU - Imran, Muhammad

AU - Asghar, Muhammad Rizwan

AU - Amer-Yahia, Sihem

AU - Castillo, Carlos

PY - 2013/1/1

Y1 - 2013/1/1

N2 - We present Tweet4act, a system to detect and classify crisis-related messages communicated over a microblogging platform. Our system relies on extracting content features from each message. These features and the use of an incident-specific dictionary allow us to determine the period type of an incident that each message belongs to. The period types are: Pre-incident (messages talking about prevention, mitigation, and preparedness), during-incident (messages sent while the incident is taking place), and post-incident (messages related to the response, recovery, and reconstruction). We show that our detection method can effectively identify incident-related messages with high precision and recall, and that our incident-period classification method outperforms standard machine learning classification methods.

AB - We present Tweet4act, a system to detect and classify crisis-related messages communicated over a microblogging platform. Our system relies on extracting content features from each message. These features and the use of an incident-specific dictionary allow us to determine the period type of an incident that each message belongs to. The period types are: Pre-incident (messages talking about prevention, mitigation, and preparedness), during-incident (messages sent while the incident is taking place), and post-incident (messages related to the response, recovery, and reconstruction). We show that our detection method can effectively identify incident-related messages with high precision and recall, and that our incident-period classification method outperforms standard machine learning classification methods.

KW - Crisis informatics

KW - Disaster management

KW - Microblogging

KW - Twitter data-analytics

UR - http://www.scopus.com/inward/record.url?scp=84905670750&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905670750&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9783923704804

SP - 834

EP - 839

BT - ISCRAM 2013 Conference Proceedings - 10th International Conference on Information Systems for Crisis Response and Management

PB - Karlsruher Institut fur Technologie (KIT)

ER -