Tweeting the terror: modelling the social media reaction to the Woolwich terrorist attack

Pete Burnap; Matthew L. Williams; Luke Sloan; Omer Rana; William Housley; Adam Edwards; Vincent Knight; Rob Procter; Alexander Voss

doi:10.1007/s13278-014-0206-4

Tweeting the terror: modelling the social media reaction to the Woolwich terrorist attack

Pete Burnap
, Matthew L. Williams
, Luke Sloan
, Omer Rana
, William Housley
, Adam Edwards
, Vincent Knight
, Rob Procter
, Alexander Voss

School of Computer Science

Research output: Contribution to journal › Article › peer-review

Abstract

Little is currently known about the factors that promote the propagation of information in online social networks following terrorist events. In this paper we took the case of the terrorist event in Woolwich, London in 2013 and built models to predict information flow size and survival using data derived from the popular social networking site Twitter. We define information flows as the propagation over time of information posted to Twitter via the action of retweeting. Following a comparison with different predictive methods, and due to the distribution exhibited by our dependent size measure, we used the zerotruncated negative binomial (ZTNB) regression method. To model survival, the Cox regression technique was used because it estimates proportional hazard rates for independent measures. Following a principal component analysis
to reduce the dimensionality of the data, social, temporal and content factors of the tweet were used as predictors in both models. Given the likely emotive

Original language	English
Article number	206
Number of pages	14
Journal	Social Network Analysis and Mining
Volume	4
Issue number	1
Early online date	13 Jun 2014
DOIs	https://doi.org/10.1007/s13278-014-0206-4
Publication status	Published - Jun 2014

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 16 Peace, Justice and Strong Institutions

Keywords

Social network analysis
Twitter
Information flows
Information propagation
Information spreading
Social media
Sentiment analysis
Opinion mining
Predictive models

Access to Document

10.1007/s13278-014-0206-4

burnap2014socnetwanalmin206
Copyright The Author(s) 2014. This article is published with open access at Springerlink.com. This article is distributed under the terms of the Creative Commons Attribution License which permits any use, distribution, and reproduction in any medium, provided the original author(s) and the source are credited.
Final published version, 569 KB

Handle.net

Persistent link to portal record

Cite this

@article{e4fec9d324694469a7c2a9ebcf1064cb,

title = "Tweeting the terror: modelling the social media reaction to the Woolwich terrorist attack",

abstract = "Little is currently known about the factors that promote the propagation of information in online social networks following terrorist events. In this paper we took the case of the terrorist event in Woolwich, London in 2013 and built models to predict information flow size and survival using data derived from the popular social networking site Twitter. We define information flows as the propagation over time of information posted to Twitter via the action of retweeting. Following a comparison with different predictive methods, and due to the distribution exhibited by our dependent size measure, we used the zerotruncated negative binomial (ZTNB) regression method. To model survival, the Cox regression technique was used because it estimates proportional hazard rates for independent measures. Following a principal component analysis to reduce the dimensionality of the data, social, temporal and content factors of the tweet were used as predictors in both models. Given the likely emotive",

keywords = "Social network analysis, Twitter, Information flows, Information propagation, Information spreading, Social media, Sentiment analysis, Opinion mining, Predictive models",

author = "Pete Burnap and Williams, \{Matthew L.\} and Luke Sloan and Omer Rana and William Housley and Adam Edwards and Vincent Knight and Rob Procter and Alexander Voss",

note = "Date of Acceptance: 23/05/2014",

year = "2014",

month = jun,

doi = "10.1007/s13278-014-0206-4",

language = "English",

volume = "4",

journal = "Social Network Analysis and Mining",

issn = "1869-5450",

publisher = "Springer-Verlag Wien",

number = "1",

}

TY - JOUR

T1 - Tweeting the terror

T2 - modelling the social media reaction to the Woolwich terrorist attack

AU - Burnap, Pete

AU - Williams, Matthew L.

AU - Sloan, Luke

AU - Rana, Omer

AU - Housley, William

AU - Edwards, Adam

AU - Knight, Vincent

AU - Procter, Rob

AU - Voss, Alexander

N1 - Date of Acceptance: 23/05/2014

PY - 2014/6

Y1 - 2014/6

N2 - Little is currently known about the factors that promote the propagation of information in online social networks following terrorist events. In this paper we took the case of the terrorist event in Woolwich, London in 2013 and built models to predict information flow size and survival using data derived from the popular social networking site Twitter. We define information flows as the propagation over time of information posted to Twitter via the action of retweeting. Following a comparison with different predictive methods, and due to the distribution exhibited by our dependent size measure, we used the zerotruncated negative binomial (ZTNB) regression method. To model survival, the Cox regression technique was used because it estimates proportional hazard rates for independent measures. Following a principal component analysis to reduce the dimensionality of the data, social, temporal and content factors of the tweet were used as predictors in both models. Given the likely emotive

AB - Little is currently known about the factors that promote the propagation of information in online social networks following terrorist events. In this paper we took the case of the terrorist event in Woolwich, London in 2013 and built models to predict information flow size and survival using data derived from the popular social networking site Twitter. We define information flows as the propagation over time of information posted to Twitter via the action of retweeting. Following a comparison with different predictive methods, and due to the distribution exhibited by our dependent size measure, we used the zerotruncated negative binomial (ZTNB) regression method. To model survival, the Cox regression technique was used because it estimates proportional hazard rates for independent measures. Following a principal component analysis to reduce the dimensionality of the data, social, temporal and content factors of the tweet were used as predictors in both models. Given the likely emotive

KW - Social network analysis

KW - Twitter

KW - Information flows

KW - Information propagation

KW - Information spreading

KW - Social media

KW - Sentiment analysis

KW - Opinion mining

KW - Predictive models

U2 - 10.1007/s13278-014-0206-4

DO - 10.1007/s13278-014-0206-4

M3 - Article

SN - 1869-5450

VL - 4

JO - Social Network Analysis and Mining

JF - Social Network Analysis and Mining

IS - 1

M1 - 206

ER -

Tweeting the terror: modelling the social media reaction to the Woolwich terrorist attack

Abstract

UN SDGs

Keywords

Access to Document

Handle.net

Fingerprint

Cite this