Automatic identification of eyewitness messages on twitter during disasters

Kiran Zahra, Muhammad Imran, F.O. Ostermann

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Social media platforms such as Twitter provide convenient ways to share and consume important information during disasters and emergencies. Information from bystanders and eyewitnesses can be useful for law enforcement agencies and humanitarian organizations to get firsthand and credible information about an ongoing situation to gain situational awareness among other potential uses. However, the identification of eyewitness reports on Twitter is a challenging task. This work investigates different types of sources on tweets related to eyewitnesses and classifies them into three types (i) direct eyewitnesses, (ii) indirect eyewitnesses, and (iii) vulnerable eyewitnesses. Moreover, we investigate various characteristics associated with each kind of eyewitness type. We observe that words related to perceptual senses (feeling, seeing, hearing) tend to be present in direct eyewitness messages, whereas emotions, thoughts, and prayers are more common in indirect witnesses. We use these characteristics and labeled data to train several machine learning classifiers. Our results performed on several real-world Twitter datasets reveal that textual features (bag-of-words) when combined with domain-expert features achieve better classification performance. Our approach contributes a successful example for combining crowdsourced and machine learning analysis, and increases our understanding and capability of identifying valuable eyewitness reports during disasters.
Original languageEnglish
Article number102107
Pages (from-to)1-15
Number of pages15
JournalInformation processing & management
Volume57
Issue number1
Early online date27 Sep 2019
DOIs
Publication statusE-pub ahead of print/First online - 27 Sep 2019

Fingerprint

twitter
Disasters
Learning systems
disaster
Audition
Law enforcement
Classifiers
social media
law enforcement
witness
learning
emotion
expert
performance
Disaster
Twitter
Machine learning

Keywords

  • ITC-ISI-JOURNAL-ARTICLE

Cite this

@article{30caa0e841c747d2bc4e98abe52a6b09,
title = "Automatic identification of eyewitness messages on twitter during disasters",
abstract = "Social media platforms such as Twitter provide convenient ways to share and consume important information during disasters and emergencies. Information from bystanders and eyewitnesses can be useful for law enforcement agencies and humanitarian organizations to get firsthand and credible information about an ongoing situation to gain situational awareness among other potential uses. However, the identification of eyewitness reports on Twitter is a challenging task. This work investigates different types of sources on tweets related to eyewitnesses and classifies them into three types (i) direct eyewitnesses, (ii) indirect eyewitnesses, and (iii) vulnerable eyewitnesses. Moreover, we investigate various characteristics associated with each kind of eyewitness type. We observe that words related to perceptual senses (feeling, seeing, hearing) tend to be present in direct eyewitness messages, whereas emotions, thoughts, and prayers are more common in indirect witnesses. We use these characteristics and labeled data to train several machine learning classifiers. Our results performed on several real-world Twitter datasets reveal that textual features (bag-of-words) when combined with domain-expert features achieve better classification performance. Our approach contributes a successful example for combining crowdsourced and machine learning analysis, and increases our understanding and capability of identifying valuable eyewitness reports during disasters.",
keywords = "ITC-ISI-JOURNAL-ARTICLE",
author = "Kiran Zahra and Muhammad Imran and F.O. Ostermann",
year = "2019",
month = "9",
day = "27",
doi = "10.1016/j.ipm.2019.102107",
language = "English",
volume = "57",
pages = "1--15",
journal = "Information processing & management",
issn = "0306-4573",
publisher = "Elsevier",
number = "1",

}

Automatic identification of eyewitness messages on twitter during disasters. / Zahra, Kiran; Imran, Muhammad; Ostermann, F.O.

In: Information processing & management, Vol. 57, No. 1, 102107, 01.01.2020, p. 1-15.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Automatic identification of eyewitness messages on twitter during disasters

AU - Zahra, Kiran

AU - Imran, Muhammad

AU - Ostermann, F.O.

PY - 2019/9/27

Y1 - 2019/9/27

N2 - Social media platforms such as Twitter provide convenient ways to share and consume important information during disasters and emergencies. Information from bystanders and eyewitnesses can be useful for law enforcement agencies and humanitarian organizations to get firsthand and credible information about an ongoing situation to gain situational awareness among other potential uses. However, the identification of eyewitness reports on Twitter is a challenging task. This work investigates different types of sources on tweets related to eyewitnesses and classifies them into three types (i) direct eyewitnesses, (ii) indirect eyewitnesses, and (iii) vulnerable eyewitnesses. Moreover, we investigate various characteristics associated with each kind of eyewitness type. We observe that words related to perceptual senses (feeling, seeing, hearing) tend to be present in direct eyewitness messages, whereas emotions, thoughts, and prayers are more common in indirect witnesses. We use these characteristics and labeled data to train several machine learning classifiers. Our results performed on several real-world Twitter datasets reveal that textual features (bag-of-words) when combined with domain-expert features achieve better classification performance. Our approach contributes a successful example for combining crowdsourced and machine learning analysis, and increases our understanding and capability of identifying valuable eyewitness reports during disasters.

AB - Social media platforms such as Twitter provide convenient ways to share and consume important information during disasters and emergencies. Information from bystanders and eyewitnesses can be useful for law enforcement agencies and humanitarian organizations to get firsthand and credible information about an ongoing situation to gain situational awareness among other potential uses. However, the identification of eyewitness reports on Twitter is a challenging task. This work investigates different types of sources on tweets related to eyewitnesses and classifies them into three types (i) direct eyewitnesses, (ii) indirect eyewitnesses, and (iii) vulnerable eyewitnesses. Moreover, we investigate various characteristics associated with each kind of eyewitness type. We observe that words related to perceptual senses (feeling, seeing, hearing) tend to be present in direct eyewitness messages, whereas emotions, thoughts, and prayers are more common in indirect witnesses. We use these characteristics and labeled data to train several machine learning classifiers. Our results performed on several real-world Twitter datasets reveal that textual features (bag-of-words) when combined with domain-expert features achieve better classification performance. Our approach contributes a successful example for combining crowdsourced and machine learning analysis, and increases our understanding and capability of identifying valuable eyewitness reports during disasters.

KW - ITC-ISI-JOURNAL-ARTICLE

UR - https://ezproxy2.utwente.nl/login?url=https://doi.org/10.1016/j.ipm.2019.102107

UR - https://ezproxy2.utwente.nl/login?url=https://library.itc.utwente.nl/login/2020/isi/ostermann_aut.pdf

U2 - 10.1016/j.ipm.2019.102107

DO - 10.1016/j.ipm.2019.102107

M3 - Article

VL - 57

SP - 1

EP - 15

JO - Information processing & management

JF - Information processing & management

SN - 0306-4573

IS - 1

M1 - 102107

ER -