Building a crisis management term resource for social media

The case of floods and protests

Irina Temnikova, Andrea Varga, Dogan Biyikli

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

3 Citations (Scopus)

Abstract

Extracting information from social media is being currently exploited for a variety of tasks, including the recognition of emergency events in Twitter. This is done in order to supply Crisis Management agencies with additional crisis information. The existing approaches, however, mostly rely on geographic location and hashtags/keywords, obtained via a manual Twitter search. As we expect that Twitter crisis terminology would differ from existing crisis glossaries, we start collecting a specialized terminological resource to support this task. The aim of this resource is to contain sets of crisis-related Twitter terms which are the same for different instances of the same type of event. This article presents a preliminary investigation of the nature of terms used in four events of two crisis types, tests manual and automatic ways to collect these terms and comes up with an initial collection of terms for these two types of events. As contributions, a novel annotation schema is presented, along with important insights into the differences in annotations between different specialists, descriptive term statistics, and performance results of existing automatic terminology recognition approaches for this task.

Original languageEnglish
Title of host publicationProceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014
PublisherEuropean Language Resources Association (ELRA)
Pages740-747
Number of pages8
ISBN (Electronic)9782951740884
Publication statusPublished - 1 Jan 2014
Event9th International Conference on Language Resources and Evaluation, LREC 2014 - Reykjavik, Iceland
Duration: 26 May 201431 May 2014

Other

Other9th International Conference on Language Resources and Evaluation, LREC 2014
CountryIceland
CityReykjavik
Period26/5/1431/5/14

Fingerprint

social media
protest
natural disaster
twitter
management
resources
event
technical language
Social Media
Protest
Resources
Crisis Management
statistics
performance
Annotation

Keywords

  • Crisis informatics
  • Social media
  • Terminology extraction

ASJC Scopus subject areas

  • Linguistics and Language
  • Library and Information Sciences
  • Education
  • Language and Linguistics

Cite this

Temnikova, I., Varga, A., & Biyikli, D. (2014). Building a crisis management term resource for social media: The case of floods and protests. In Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014 (pp. 740-747). European Language Resources Association (ELRA).

Building a crisis management term resource for social media : The case of floods and protests. / Temnikova, Irina; Varga, Andrea; Biyikli, Dogan.

Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014. European Language Resources Association (ELRA), 2014. p. 740-747.

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

Temnikova, I, Varga, A & Biyikli, D 2014, Building a crisis management term resource for social media: The case of floods and protests. in Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014. European Language Resources Association (ELRA), pp. 740-747, 9th International Conference on Language Resources and Evaluation, LREC 2014, Reykjavik, Iceland, 26/5/14.
Temnikova I, Varga A, Biyikli D. Building a crisis management term resource for social media: The case of floods and protests. In Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014. European Language Resources Association (ELRA). 2014. p. 740-747
Temnikova, Irina ; Varga, Andrea ; Biyikli, Dogan. / Building a crisis management term resource for social media : The case of floods and protests. Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014. European Language Resources Association (ELRA), 2014. pp. 740-747
@inproceedings{bf80e7852be446a49c5c65c5e3434e06,
title = "Building a crisis management term resource for social media: The case of floods and protests",
abstract = "Extracting information from social media is being currently exploited for a variety of tasks, including the recognition of emergency events in Twitter. This is done in order to supply Crisis Management agencies with additional crisis information. The existing approaches, however, mostly rely on geographic location and hashtags/keywords, obtained via a manual Twitter search. As we expect that Twitter crisis terminology would differ from existing crisis glossaries, we start collecting a specialized terminological resource to support this task. The aim of this resource is to contain sets of crisis-related Twitter terms which are the same for different instances of the same type of event. This article presents a preliminary investigation of the nature of terms used in four events of two crisis types, tests manual and automatic ways to collect these terms and comes up with an initial collection of terms for these two types of events. As contributions, a novel annotation schema is presented, along with important insights into the differences in annotations between different specialists, descriptive term statistics, and performance results of existing automatic terminology recognition approaches for this task.",
keywords = "Crisis informatics, Social media, Terminology extraction",
author = "Irina Temnikova and Andrea Varga and Dogan Biyikli",
year = "2014",
month = "1",
day = "1",
language = "English",
pages = "740--747",
booktitle = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
publisher = "European Language Resources Association (ELRA)",

}

TY - GEN

T1 - Building a crisis management term resource for social media

T2 - The case of floods and protests

AU - Temnikova, Irina

AU - Varga, Andrea

AU - Biyikli, Dogan

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Extracting information from social media is being currently exploited for a variety of tasks, including the recognition of emergency events in Twitter. This is done in order to supply Crisis Management agencies with additional crisis information. The existing approaches, however, mostly rely on geographic location and hashtags/keywords, obtained via a manual Twitter search. As we expect that Twitter crisis terminology would differ from existing crisis glossaries, we start collecting a specialized terminological resource to support this task. The aim of this resource is to contain sets of crisis-related Twitter terms which are the same for different instances of the same type of event. This article presents a preliminary investigation of the nature of terms used in four events of two crisis types, tests manual and automatic ways to collect these terms and comes up with an initial collection of terms for these two types of events. As contributions, a novel annotation schema is presented, along with important insights into the differences in annotations between different specialists, descriptive term statistics, and performance results of existing automatic terminology recognition approaches for this task.

AB - Extracting information from social media is being currently exploited for a variety of tasks, including the recognition of emergency events in Twitter. This is done in order to supply Crisis Management agencies with additional crisis information. The existing approaches, however, mostly rely on geographic location and hashtags/keywords, obtained via a manual Twitter search. As we expect that Twitter crisis terminology would differ from existing crisis glossaries, we start collecting a specialized terminological resource to support this task. The aim of this resource is to contain sets of crisis-related Twitter terms which are the same for different instances of the same type of event. This article presents a preliminary investigation of the nature of terms used in four events of two crisis types, tests manual and automatic ways to collect these terms and comes up with an initial collection of terms for these two types of events. As contributions, a novel annotation schema is presented, along with important insights into the differences in annotations between different specialists, descriptive term statistics, and performance results of existing automatic terminology recognition approaches for this task.

KW - Crisis informatics

KW - Social media

KW - Terminology extraction

UR - http://www.scopus.com/inward/record.url?scp=84968633125&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84968633125&partnerID=8YFLogxK

M3 - Conference contribution

SP - 740

EP - 747

BT - Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014

PB - European Language Resources Association (ELRA)

ER -