Predicting ideological friends and foes in twitter conflicts

Zhe Liu, Ingmar Weber

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

6 Citations (Scopus)

Abstract

The rise in popularity of Twitter in recent years has in parallel led to an increase in online controversies. To monitor and control such conflicts early on, we design and evaluate a language-agnostic classifier to tell pairs of ideological friends from foes. We build the classifier using features from four different aspects: user-based, interaction-based, relationship-based and conflict-based. By experimenting with three large data sets containing diverse conflicts, we demonstrate the effectiveness of language-agnostic classification of ideological relation, achieving satisfactory results across all three data sets. Such a classifier potentially enables studies of diverse conflicts on Twitter on a large scale.

Original languageEnglish
Title of host publicationWWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web
PublisherAssociation for Computing Machinery, Inc
Pages575-576
Number of pages2
ISBN (Electronic)9781450327459
DOIs
Publication statusPublished - 7 Apr 2014
Event23rd International Conference on World Wide Web, WWW 2014 - Seoul, Korea, Republic of
Duration: 7 Apr 201411 Apr 2014

Other

Other23rd International Conference on World Wide Web, WWW 2014
CountryKorea, Republic of
CitySeoul
Period7/4/1411/4/14

Fingerprint

Classifiers

Keywords

  • Classification
  • Conflict
  • Political ideology
  • Social network
  • Twitter

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software

Cite this

Liu, Z., & Weber, I. (2014). Predicting ideological friends and foes in twitter conflicts. In WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web (pp. 575-576). Association for Computing Machinery, Inc. https://doi.org/10.1145/2567948.2576964

Predicting ideological friends and foes in twitter conflicts. / Liu, Zhe; Weber, Ingmar.

WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web. Association for Computing Machinery, Inc, 2014. p. 575-576.

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

Liu, Z & Weber, I 2014, Predicting ideological friends and foes in twitter conflicts. in WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web. Association for Computing Machinery, Inc, pp. 575-576, 23rd International Conference on World Wide Web, WWW 2014, Seoul, Korea, Republic of, 7/4/14. https://doi.org/10.1145/2567948.2576964
Liu Z, Weber I. Predicting ideological friends and foes in twitter conflicts. In WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web. Association for Computing Machinery, Inc. 2014. p. 575-576 https://doi.org/10.1145/2567948.2576964
Liu, Zhe ; Weber, Ingmar. / Predicting ideological friends and foes in twitter conflicts. WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web. Association for Computing Machinery, Inc, 2014. pp. 575-576
@inproceedings{63a9e3d71578483a8131212f63c16926,
title = "Predicting ideological friends and foes in twitter conflicts",
abstract = "The rise in popularity of Twitter in recent years has in parallel led to an increase in online controversies. To monitor and control such conflicts early on, we design and evaluate a language-agnostic classifier to tell pairs of ideological friends from foes. We build the classifier using features from four different aspects: user-based, interaction-based, relationship-based and conflict-based. By experimenting with three large data sets containing diverse conflicts, we demonstrate the effectiveness of language-agnostic classification of ideological relation, achieving satisfactory results across all three data sets. Such a classifier potentially enables studies of diverse conflicts on Twitter on a large scale.",
keywords = "Classification, Conflict, Political ideology, Social network, Twitter",
author = "Zhe Liu and Ingmar Weber",
year = "2014",
month = "4",
day = "7",
doi = "10.1145/2567948.2576964",
language = "English",
pages = "575--576",
booktitle = "WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Predicting ideological friends and foes in twitter conflicts

AU - Liu, Zhe

AU - Weber, Ingmar

PY - 2014/4/7

Y1 - 2014/4/7

N2 - The rise in popularity of Twitter in recent years has in parallel led to an increase in online controversies. To monitor and control such conflicts early on, we design and evaluate a language-agnostic classifier to tell pairs of ideological friends from foes. We build the classifier using features from four different aspects: user-based, interaction-based, relationship-based and conflict-based. By experimenting with three large data sets containing diverse conflicts, we demonstrate the effectiveness of language-agnostic classification of ideological relation, achieving satisfactory results across all three data sets. Such a classifier potentially enables studies of diverse conflicts on Twitter on a large scale.

AB - The rise in popularity of Twitter in recent years has in parallel led to an increase in online controversies. To monitor and control such conflicts early on, we design and evaluate a language-agnostic classifier to tell pairs of ideological friends from foes. We build the classifier using features from four different aspects: user-based, interaction-based, relationship-based and conflict-based. By experimenting with three large data sets containing diverse conflicts, we demonstrate the effectiveness of language-agnostic classification of ideological relation, achieving satisfactory results across all three data sets. Such a classifier potentially enables studies of diverse conflicts on Twitter on a large scale.

KW - Classification

KW - Conflict

KW - Political ideology

KW - Social network

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84990944677&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84990944677&partnerID=8YFLogxK

U2 - 10.1145/2567948.2576964

DO - 10.1145/2567948.2576964

M3 - Conference contribution

SP - 575

EP - 576

BT - WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web

PB - Association for Computing Machinery, Inc

ER -