Crisis management knowledge from social media

Karl Kreiner, Aapo Immonen, Hanna Suominen

Research output: A Conference proceeding or a Chapter in BookConference contribution

5 Citations (Scopus)

Abstract

More and more crisis managers, crisis communicators and laypeople use Twitter and other social media to provide or seek crisis information. In this paper, we focus on retrospective conversion of human-safety related data to crisis management knowledge. First, we study how Twitter data can be classified into the seven categories of the United Nations Development Program Security Model (i.e., Food, Health, Politics, Economic, Personal, Community, and Environment). We conclude that these topic categories are applicable, and supplementing them with classification of individual authors into more generic sources of data (i.e., Official authorities, Media, and Laypeople) allows curating data and assessing crisis maturity. Second, we introduce automated classifiers, based on supervised learning and decision rules, for both tasks and evaluate their correctness. This evaluation uses two datasets collected during the crises of Queensland floods and NZ Earthquake in 2011. The topic classifier performs well in the major categories (i.e., 120-190 training instances) of Economic (F = 0.76) and Community (F = 0.67) while in the minor categories (i.e., 0-60 training instances) the results are more modest (F ≤ 0.41). The classifier shows excellent results (F ≥ 0.83) in all categories.

Original languageEnglish
Title of host publicationADCS 2013 - Proceedings of the 18th Australasian Document Computing Symposium
PublisherACM Association for Computing Machinery
Pages105-108
Number of pages4
ISBN (Print)9781450325240
DOIs
Publication statusPublished - 5 Dec 2013
Event18th Australasian Document Computing Symposium, ADCS 2013 - Brisbane, Brisbane, Australia
Duration: 5 Dec 20136 Dec 2013

Conference

Conference18th Australasian Document Computing Symposium, ADCS 2013
Abbreviated titleADCS
CountryAustralia
CityBrisbane
Period5/12/136/12/13

Fingerprint

Knowledge management
Classifiers
Economics
Supervised learning
Earthquakes
Managers
Health

Cite this

Kreiner, K., Immonen, A., & Suominen, H. (2013). Crisis management knowledge from social media. In ADCS 2013 - Proceedings of the 18th Australasian Document Computing Symposium (pp. 105-108). ACM Association for Computing Machinery. https://doi.org/10.1145/2537734.2537740
Kreiner, Karl ; Immonen, Aapo ; Suominen, Hanna. / Crisis management knowledge from social media. ADCS 2013 - Proceedings of the 18th Australasian Document Computing Symposium. ACM Association for Computing Machinery, 2013. pp. 105-108
@inproceedings{fa08ca54c8044eb5ac6ea958db74c399,
title = "Crisis management knowledge from social media",
abstract = "More and more crisis managers, crisis communicators and laypeople use Twitter and other social media to provide or seek crisis information. In this paper, we focus on retrospective conversion of human-safety related data to crisis management knowledge. First, we study how Twitter data can be classified into the seven categories of the United Nations Development Program Security Model (i.e., Food, Health, Politics, Economic, Personal, Community, and Environment). We conclude that these topic categories are applicable, and supplementing them with classification of individual authors into more generic sources of data (i.e., Official authorities, Media, and Laypeople) allows curating data and assessing crisis maturity. Second, we introduce automated classifiers, based on supervised learning and decision rules, for both tasks and evaluate their correctness. This evaluation uses two datasets collected during the crises of Queensland floods and NZ Earthquake in 2011. The topic classifier performs well in the major categories (i.e., 120-190 training instances) of Economic (F = 0.76) and Community (F = 0.67) while in the minor categories (i.e., 0-60 training instances) the results are more modest (F ≤ 0.41). The classifier shows excellent results (F ≥ 0.83) in all categories.",
keywords = "Data processing, Information retrieval, Knowledge management, Social network services",
author = "Karl Kreiner and Aapo Immonen and Hanna Suominen",
year = "2013",
month = "12",
day = "5",
doi = "10.1145/2537734.2537740",
language = "English",
isbn = "9781450325240",
pages = "105--108",
booktitle = "ADCS 2013 - Proceedings of the 18th Australasian Document Computing Symposium",
publisher = "ACM Association for Computing Machinery",

}

Kreiner, K, Immonen, A & Suominen, H 2013, Crisis management knowledge from social media. in ADCS 2013 - Proceedings of the 18th Australasian Document Computing Symposium. ACM Association for Computing Machinery, pp. 105-108, 18th Australasian Document Computing Symposium, ADCS 2013, Brisbane, Australia, 5/12/13. https://doi.org/10.1145/2537734.2537740

Crisis management knowledge from social media. / Kreiner, Karl; Immonen, Aapo; Suominen, Hanna.

ADCS 2013 - Proceedings of the 18th Australasian Document Computing Symposium. ACM Association for Computing Machinery, 2013. p. 105-108.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Crisis management knowledge from social media

AU - Kreiner, Karl

AU - Immonen, Aapo

AU - Suominen, Hanna

PY - 2013/12/5

Y1 - 2013/12/5

N2 - More and more crisis managers, crisis communicators and laypeople use Twitter and other social media to provide or seek crisis information. In this paper, we focus on retrospective conversion of human-safety related data to crisis management knowledge. First, we study how Twitter data can be classified into the seven categories of the United Nations Development Program Security Model (i.e., Food, Health, Politics, Economic, Personal, Community, and Environment). We conclude that these topic categories are applicable, and supplementing them with classification of individual authors into more generic sources of data (i.e., Official authorities, Media, and Laypeople) allows curating data and assessing crisis maturity. Second, we introduce automated classifiers, based on supervised learning and decision rules, for both tasks and evaluate their correctness. This evaluation uses two datasets collected during the crises of Queensland floods and NZ Earthquake in 2011. The topic classifier performs well in the major categories (i.e., 120-190 training instances) of Economic (F = 0.76) and Community (F = 0.67) while in the minor categories (i.e., 0-60 training instances) the results are more modest (F ≤ 0.41). The classifier shows excellent results (F ≥ 0.83) in all categories.

AB - More and more crisis managers, crisis communicators and laypeople use Twitter and other social media to provide or seek crisis information. In this paper, we focus on retrospective conversion of human-safety related data to crisis management knowledge. First, we study how Twitter data can be classified into the seven categories of the United Nations Development Program Security Model (i.e., Food, Health, Politics, Economic, Personal, Community, and Environment). We conclude that these topic categories are applicable, and supplementing them with classification of individual authors into more generic sources of data (i.e., Official authorities, Media, and Laypeople) allows curating data and assessing crisis maturity. Second, we introduce automated classifiers, based on supervised learning and decision rules, for both tasks and evaluate their correctness. This evaluation uses two datasets collected during the crises of Queensland floods and NZ Earthquake in 2011. The topic classifier performs well in the major categories (i.e., 120-190 training instances) of Economic (F = 0.76) and Community (F = 0.67) while in the minor categories (i.e., 0-60 training instances) the results are more modest (F ≤ 0.41). The classifier shows excellent results (F ≥ 0.83) in all categories.

KW - Data processing

KW - Information retrieval

KW - Knowledge management

KW - Social network services

UR - http://www.scopus.com/inward/record.url?scp=84892739492&partnerID=8YFLogxK

U2 - 10.1145/2537734.2537740

DO - 10.1145/2537734.2537740

M3 - Conference contribution

SN - 9781450325240

SP - 105

EP - 108

BT - ADCS 2013 - Proceedings of the 18th Australasian Document Computing Symposium

PB - ACM Association for Computing Machinery

ER -

Kreiner K, Immonen A, Suominen H. Crisis management knowledge from social media. In ADCS 2013 - Proceedings of the 18th Australasian Document Computing Symposium. ACM Association for Computing Machinery. 2013. p. 105-108 https://doi.org/10.1145/2537734.2537740