#ISISisNotIslam or #DeportAllMuslims? Predicting unspoken views

Walid Magdy, Kareem Darwish, Norah Abokhodair, Afshin Rahimi, Timothy Baldwin

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

17 Citations (Scopus)

Abstract

This paper examines the effect of online social network interactions on future attitudes. Specifically, we focus on how a person's online content and network dynamics can be used to predict future attitudes and stances in the aftermath of a major event. In this study, we focus on the attitudes of US Twitter users towards Islam and Muslims subsequent to the tragic Paris terrorist attacks that occurred on November 13, 2015. We quantitatively analyze 44K users' network interactions and historical tweets to predict their attitudes. We provide a description of the quantitative results based on the content (hashtags) and network interaction (retweets, replies, and mentions). We analyze two types of data: (1) we use post-event tweets to learn users' stated stances towards Muslims based on sampling methods and crowd-sourced annotations; and (2) we employ pre-event interactions on Twitter to build a classifier to predict post-event stances. We found that pre-event network interactions can predict someone's attitudes towards Muslims with 82% macro F-measure, even in the absence of prior mentions of Islam, Muslims, or related terms.

Original languageEnglish
Title of host publicationWebSci 2016 - Proceedings of the 2016 ACM Web Science Conference
PublisherAssociation for Computing Machinery, Inc
Pages95-106
Number of pages12
ISBN (Electronic)9781450342087
DOIs
Publication statusPublished - 22 May 2016
Event8th ACM Web Science Conference, WebSci 2016 - Hannover, Germany
Duration: 22 May 201625 May 2016

Other

Other8th ACM Web Science Conference, WebSci 2016
CountryGermany
CityHannover
Period22/5/1625/5/16

Fingerprint

Macros
Classifiers
Sampling

Keywords

  • Homophily
  • Network analysis
  • Paris attacks
  • Social influence
  • Stance prediction
  • Twitter data analysis

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Magdy, W., Darwish, K., Abokhodair, N., Rahimi, A., & Baldwin, T. (2016). #ISISisNotIslam or #DeportAllMuslims? Predicting unspoken views. In WebSci 2016 - Proceedings of the 2016 ACM Web Science Conference (pp. 95-106). Association for Computing Machinery, Inc. https://doi.org/10.1145/2908131.2908150

#ISISisNotIslam or #DeportAllMuslims? Predicting unspoken views. / Magdy, Walid; Darwish, Kareem; Abokhodair, Norah; Rahimi, Afshin; Baldwin, Timothy.

WebSci 2016 - Proceedings of the 2016 ACM Web Science Conference. Association for Computing Machinery, Inc, 2016. p. 95-106.

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

Magdy, W, Darwish, K, Abokhodair, N, Rahimi, A & Baldwin, T 2016, #ISISisNotIslam or #DeportAllMuslims? Predicting unspoken views. in WebSci 2016 - Proceedings of the 2016 ACM Web Science Conference. Association for Computing Machinery, Inc, pp. 95-106, 8th ACM Web Science Conference, WebSci 2016, Hannover, Germany, 22/5/16. https://doi.org/10.1145/2908131.2908150
Magdy W, Darwish K, Abokhodair N, Rahimi A, Baldwin T. #ISISisNotIslam or #DeportAllMuslims? Predicting unspoken views. In WebSci 2016 - Proceedings of the 2016 ACM Web Science Conference. Association for Computing Machinery, Inc. 2016. p. 95-106 https://doi.org/10.1145/2908131.2908150
Magdy, Walid ; Darwish, Kareem ; Abokhodair, Norah ; Rahimi, Afshin ; Baldwin, Timothy. / #ISISisNotIslam or #DeportAllMuslims? Predicting unspoken views. WebSci 2016 - Proceedings of the 2016 ACM Web Science Conference. Association for Computing Machinery, Inc, 2016. pp. 95-106
@inproceedings{5849d1266ea140cbad31cfd27346fba6,
title = "#ISISisNotIslam or #DeportAllMuslims? Predicting unspoken views",
abstract = "This paper examines the effect of online social network interactions on future attitudes. Specifically, we focus on how a person's online content and network dynamics can be used to predict future attitudes and stances in the aftermath of a major event. In this study, we focus on the attitudes of US Twitter users towards Islam and Muslims subsequent to the tragic Paris terrorist attacks that occurred on November 13, 2015. We quantitatively analyze 44K users' network interactions and historical tweets to predict their attitudes. We provide a description of the quantitative results based on the content (hashtags) and network interaction (retweets, replies, and mentions). We analyze two types of data: (1) we use post-event tweets to learn users' stated stances towards Muslims based on sampling methods and crowd-sourced annotations; and (2) we employ pre-event interactions on Twitter to build a classifier to predict post-event stances. We found that pre-event network interactions can predict someone's attitudes towards Muslims with 82{\%} macro F-measure, even in the absence of prior mentions of Islam, Muslims, or related terms.",
keywords = "Homophily, Network analysis, Paris attacks, Social influence, Stance prediction, Twitter data analysis",
author = "Walid Magdy and Kareem Darwish and Norah Abokhodair and Afshin Rahimi and Timothy Baldwin",
year = "2016",
month = "5",
day = "22",
doi = "10.1145/2908131.2908150",
language = "English",
pages = "95--106",
booktitle = "WebSci 2016 - Proceedings of the 2016 ACM Web Science Conference",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - #ISISisNotIslam or #DeportAllMuslims? Predicting unspoken views

AU - Magdy, Walid

AU - Darwish, Kareem

AU - Abokhodair, Norah

AU - Rahimi, Afshin

AU - Baldwin, Timothy

PY - 2016/5/22

Y1 - 2016/5/22

N2 - This paper examines the effect of online social network interactions on future attitudes. Specifically, we focus on how a person's online content and network dynamics can be used to predict future attitudes and stances in the aftermath of a major event. In this study, we focus on the attitudes of US Twitter users towards Islam and Muslims subsequent to the tragic Paris terrorist attacks that occurred on November 13, 2015. We quantitatively analyze 44K users' network interactions and historical tweets to predict their attitudes. We provide a description of the quantitative results based on the content (hashtags) and network interaction (retweets, replies, and mentions). We analyze two types of data: (1) we use post-event tweets to learn users' stated stances towards Muslims based on sampling methods and crowd-sourced annotations; and (2) we employ pre-event interactions on Twitter to build a classifier to predict post-event stances. We found that pre-event network interactions can predict someone's attitudes towards Muslims with 82% macro F-measure, even in the absence of prior mentions of Islam, Muslims, or related terms.

AB - This paper examines the effect of online social network interactions on future attitudes. Specifically, we focus on how a person's online content and network dynamics can be used to predict future attitudes and stances in the aftermath of a major event. In this study, we focus on the attitudes of US Twitter users towards Islam and Muslims subsequent to the tragic Paris terrorist attacks that occurred on November 13, 2015. We quantitatively analyze 44K users' network interactions and historical tweets to predict their attitudes. We provide a description of the quantitative results based on the content (hashtags) and network interaction (retweets, replies, and mentions). We analyze two types of data: (1) we use post-event tweets to learn users' stated stances towards Muslims based on sampling methods and crowd-sourced annotations; and (2) we employ pre-event interactions on Twitter to build a classifier to predict post-event stances. We found that pre-event network interactions can predict someone's attitudes towards Muslims with 82% macro F-measure, even in the absence of prior mentions of Islam, Muslims, or related terms.

KW - Homophily

KW - Network analysis

KW - Paris attacks

KW - Social influence

KW - Stance prediction

KW - Twitter data analysis

UR - http://www.scopus.com/inward/record.url?scp=84976407476&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84976407476&partnerID=8YFLogxK

U2 - 10.1145/2908131.2908150

DO - 10.1145/2908131.2908150

M3 - Conference contribution

SP - 95

EP - 106

BT - WebSci 2016 - Proceedings of the 2016 ACM Web Science Conference

PB - Association for Computing Machinery, Inc

ER -