Discovering disaster events from social media streams

Yue Fu Tsai, Jih Liang Hsieh, Wei-Guang Teng, Ting-Wei Hou, Chih Pin Freg, Yu Chung Tsao

Research output: Contribution to journalArticle

Abstract

Natural and man-made disasters can both cause severe loss of lives and economic damage. Examples include earthquakes, floods, and road crashes. Nevertheless, rapidly and accurately identifying the latest status of a disaster event is undoubtedly one of the most difficult tasks for agencies in crisis management. In this work, we thus propose to monitor online data streams in social media to detect and track real-world events. Unlike conventional media, social media is advantageous because of its immediateness, huge data scale, and worldwide availability. Nevertheless, messages generated by netizens can be incomplete, subjective, or even error prone. Only with an appropriately designed scheme can invaluable clues embedded in huge amounts of online messages be discovered when carefully exploiting the information over content, temporal, and social dimensions. Specifically, we collect data from multiple social networks, conduct real-time analysis, and present interactive visualization. Experimental studies show that the proposed scheme is feasible for agencies in practice.

Original languageEnglish
Pages (from-to)685-701
Number of pages17
JournalInternational Journal of Industrial Engineering : Theory Applications and Practice
Volume25
Publication statusPublished - 2018 Jan 1

Fingerprint

Disasters
Earthquakes
Visualization
Availability
Economics

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering

Cite this

@article{8a8263642b2d462cb01c4d4b578dc154,
title = "Discovering disaster events from social media streams",
abstract = "Natural and man-made disasters can both cause severe loss of lives and economic damage. Examples include earthquakes, floods, and road crashes. Nevertheless, rapidly and accurately identifying the latest status of a disaster event is undoubtedly one of the most difficult tasks for agencies in crisis management. In this work, we thus propose to monitor online data streams in social media to detect and track real-world events. Unlike conventional media, social media is advantageous because of its immediateness, huge data scale, and worldwide availability. Nevertheless, messages generated by netizens can be incomplete, subjective, or even error prone. Only with an appropriately designed scheme can invaluable clues embedded in huge amounts of online messages be discovered when carefully exploiting the information over content, temporal, and social dimensions. Specifically, we collect data from multiple social networks, conduct real-time analysis, and present interactive visualization. Experimental studies show that the proposed scheme is feasible for agencies in practice.",
author = "Tsai, {Yue Fu} and Hsieh, {Jih Liang} and Wei-Guang Teng and Ting-Wei Hou and Freg, {Chih Pin} and Tsao, {Yu Chung}",
year = "2018",
month = "1",
day = "1",
language = "English",
volume = "25",
pages = "685--701",
journal = "International Journal of Industrial Engineering : Theory Applications and Practice",
issn = "1072-4761",
publisher = "University of Cincinnati",

}

Discovering disaster events from social media streams. / Tsai, Yue Fu; Hsieh, Jih Liang; Teng, Wei-Guang; Hou, Ting-Wei; Freg, Chih Pin; Tsao, Yu Chung.

In: International Journal of Industrial Engineering : Theory Applications and Practice, Vol. 25, 01.01.2018, p. 685-701.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Discovering disaster events from social media streams

AU - Tsai, Yue Fu

AU - Hsieh, Jih Liang

AU - Teng, Wei-Guang

AU - Hou, Ting-Wei

AU - Freg, Chih Pin

AU - Tsao, Yu Chung

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Natural and man-made disasters can both cause severe loss of lives and economic damage. Examples include earthquakes, floods, and road crashes. Nevertheless, rapidly and accurately identifying the latest status of a disaster event is undoubtedly one of the most difficult tasks for agencies in crisis management. In this work, we thus propose to monitor online data streams in social media to detect and track real-world events. Unlike conventional media, social media is advantageous because of its immediateness, huge data scale, and worldwide availability. Nevertheless, messages generated by netizens can be incomplete, subjective, or even error prone. Only with an appropriately designed scheme can invaluable clues embedded in huge amounts of online messages be discovered when carefully exploiting the information over content, temporal, and social dimensions. Specifically, we collect data from multiple social networks, conduct real-time analysis, and present interactive visualization. Experimental studies show that the proposed scheme is feasible for agencies in practice.

AB - Natural and man-made disasters can both cause severe loss of lives and economic damage. Examples include earthquakes, floods, and road crashes. Nevertheless, rapidly and accurately identifying the latest status of a disaster event is undoubtedly one of the most difficult tasks for agencies in crisis management. In this work, we thus propose to monitor online data streams in social media to detect and track real-world events. Unlike conventional media, social media is advantageous because of its immediateness, huge data scale, and worldwide availability. Nevertheless, messages generated by netizens can be incomplete, subjective, or even error prone. Only with an appropriately designed scheme can invaluable clues embedded in huge amounts of online messages be discovered when carefully exploiting the information over content, temporal, and social dimensions. Specifically, we collect data from multiple social networks, conduct real-time analysis, and present interactive visualization. Experimental studies show that the proposed scheme is feasible for agencies in practice.

UR - http://www.scopus.com/inward/record.url?scp=85060723675&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060723675&partnerID=8YFLogxK

M3 - Article

VL - 25

SP - 685

EP - 701

JO - International Journal of Industrial Engineering : Theory Applications and Practice

JF - International Journal of Industrial Engineering : Theory Applications and Practice

SN - 1072-4761

ER -