Abstract

The spread of harmful mis-information in social media is a pressing problem. We refer accounts that have the capability of spreading such information to viral proportions as 'Pathogenic Social Media' accounts. These accounts include terrorist supporters accounts, water armies, and fake news writers. We introduce an unsupervised causality-based framework that also leverages label propagation. This approach identifies these users without using network structure, cascade path information, content and user's information. We show our approach obtains higher precision (0.75) in identifying Pathogenic Social Media accounts in comparison with random (precision of 0.11) and existing bot detection (precision of 0.16) methods.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 1st International Conference on Data Intelligence and Security, ICDIS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages57-64
Number of pages8
ISBN (Electronic)9781538657621
DOIs
StatePublished - May 25 2018
Event1st International Conference on Data Intelligence and Security, ICDIS 2018 - South Padre Island, United States
Duration: Apr 8 2018Apr 10 2018

Other

Other1st International Conference on Data Intelligence and Security, ICDIS 2018
CountryUnited States
CitySouth Padre Island
Period4/8/184/10/18

Fingerprint

Labels
Water

Keywords

  • Causality
  • Pathogenic Social Media
  • Social Bot
  • Terrorist Accounts
  • Water Armies

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Safety, Risk, Reliability and Quality

Cite this

Shaabani, E., Guo, R., & Shakarian, P. (2018). Detecting pathogenic social media accounts without content or network structure. In Proceedings - 2018 1st International Conference on Data Intelligence and Security, ICDIS 2018 (pp. 57-64). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDIS.2018.00016

Detecting pathogenic social media accounts without content or network structure. / Shaabani, Elham; Guo, Ruocheng; Shakarian, Paulo.

Proceedings - 2018 1st International Conference on Data Intelligence and Security, ICDIS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 57-64.

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

Shaabani, E, Guo, R & Shakarian, P 2018, Detecting pathogenic social media accounts without content or network structure. in Proceedings - 2018 1st International Conference on Data Intelligence and Security, ICDIS 2018. Institute of Electrical and Electronics Engineers Inc., pp. 57-64, 1st International Conference on Data Intelligence and Security, ICDIS 2018, South Padre Island, United States, 4/8/18. https://doi.org/10.1109/ICDIS.2018.00016
Shaabani E, Guo R, Shakarian P. Detecting pathogenic social media accounts without content or network structure. In Proceedings - 2018 1st International Conference on Data Intelligence and Security, ICDIS 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 57-64 https://doi.org/10.1109/ICDIS.2018.00016
Shaabani, Elham ; Guo, Ruocheng ; Shakarian, Paulo. / Detecting pathogenic social media accounts without content or network structure. Proceedings - 2018 1st International Conference on Data Intelligence and Security, ICDIS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 57-64
@inproceedings{6837636e77cb45ff9a9d9e2c3f738cf2,
title = "Detecting pathogenic social media accounts without content or network structure",
abstract = "The spread of harmful mis-information in social media is a pressing problem. We refer accounts that have the capability of spreading such information to viral proportions as 'Pathogenic Social Media' accounts. These accounts include terrorist supporters accounts, water armies, and fake news writers. We introduce an unsupervised causality-based framework that also leverages label propagation. This approach identifies these users without using network structure, cascade path information, content and user's information. We show our approach obtains higher precision (0.75) in identifying Pathogenic Social Media accounts in comparison with random (precision of 0.11) and existing bot detection (precision of 0.16) methods.",
keywords = "Causality, Pathogenic Social Media, Social Bot, Terrorist Accounts, Water Armies",
author = "Elham Shaabani and Ruocheng Guo and Paulo Shakarian",
year = "2018",
month = "5",
day = "25",
doi = "10.1109/ICDIS.2018.00016",
language = "English (US)",
pages = "57--64",
booktitle = "Proceedings - 2018 1st International Conference on Data Intelligence and Security, ICDIS 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Detecting pathogenic social media accounts without content or network structure

AU - Shaabani, Elham

AU - Guo, Ruocheng

AU - Shakarian, Paulo

PY - 2018/5/25

Y1 - 2018/5/25

N2 - The spread of harmful mis-information in social media is a pressing problem. We refer accounts that have the capability of spreading such information to viral proportions as 'Pathogenic Social Media' accounts. These accounts include terrorist supporters accounts, water armies, and fake news writers. We introduce an unsupervised causality-based framework that also leverages label propagation. This approach identifies these users without using network structure, cascade path information, content and user's information. We show our approach obtains higher precision (0.75) in identifying Pathogenic Social Media accounts in comparison with random (precision of 0.11) and existing bot detection (precision of 0.16) methods.

AB - The spread of harmful mis-information in social media is a pressing problem. We refer accounts that have the capability of spreading such information to viral proportions as 'Pathogenic Social Media' accounts. These accounts include terrorist supporters accounts, water armies, and fake news writers. We introduce an unsupervised causality-based framework that also leverages label propagation. This approach identifies these users without using network structure, cascade path information, content and user's information. We show our approach obtains higher precision (0.75) in identifying Pathogenic Social Media accounts in comparison with random (precision of 0.11) and existing bot detection (precision of 0.16) methods.

KW - Causality

KW - Pathogenic Social Media

KW - Social Bot

KW - Terrorist Accounts

KW - Water Armies

UR - http://www.scopus.com/inward/record.url?scp=85048530365&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048530365&partnerID=8YFLogxK

U2 - 10.1109/ICDIS.2018.00016

DO - 10.1109/ICDIS.2018.00016

M3 - Conference contribution

AN - SCOPUS:85048530365

SP - 57

EP - 64

BT - Proceedings - 2018 1st International Conference on Data Intelligence and Security, ICDIS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -