AAFA

Associative affinity factor analysis for bot detection and stance classification in Twitter

Saad Sadiq, Yilin Yan, Asia Taylor, Mei-Ling Shyu, Shu Ching Chen, Daniel J Feaster

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

4 Citations (Scopus)

Abstract

The rise in popularity of social interacting websites such as Facebook, Twitter, and Snapchat has been challenged by the upsurge of unwelcomed and troubling bodies on these systems. This includes spam senders, malware systems, and other content contaminators. It is noted that highly automated accounts with 450 tweets per day produced almost 18% of entire Twitter circulation in the 2016 U.S. Presidential election. It is also observed that those disruptive systems called bots are inclined more towards circulating negative news than positive information. This paper introduces a novel framework named Associative Affinity Factor Analysis (AAFA) designed for stance detection and bot identification. Using AAFA, the proposed framework identifies real people from bots and detects the stance in bipolar affinities. The 2016 U.S. Presidential election campaign was used as a test use case because of its significant and unique counter-factual properties. The results show that our proposed AAFA framework achieves high accuracy when compared to several existing state-of-theart methods.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages356-365
Number of pages10
Volume2017-January
ISBN (Electronic)9781538615621
DOIs
StatePublished - Nov 8 2017
Event18th IEEE International Conference on Information Reuse and Integration, IRI 2017 - San Diego, United States
Duration: Aug 4 2017Aug 6 2017

Other

Other18th IEEE International Conference on Information Reuse and Integration, IRI 2017
CountryUnited States
CitySan Diego
Period8/4/178/6/17

Fingerprint

Factor analysis
Websites
Twitter
Presidential elections

Keywords

  • Association affinity
  • Bot detection
  • Factor analysis
  • Stance classification

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems and Management
  • Artificial Intelligence
  • Computer Science Applications
  • Information Systems

Cite this

Sadiq, S., Yan, Y., Taylor, A., Shyu, M-L., Chen, S. C., & Feaster, D. J. (2017). AAFA: Associative affinity factor analysis for bot detection and stance classification in Twitter. In Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017 (Vol. 2017-January, pp. 356-365). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IRI.2017.25

AAFA : Associative affinity factor analysis for bot detection and stance classification in Twitter. / Sadiq, Saad; Yan, Yilin; Taylor, Asia; Shyu, Mei-Ling; Chen, Shu Ching; Feaster, Daniel J.

Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. p. 356-365.

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

Sadiq, S, Yan, Y, Taylor, A, Shyu, M-L, Chen, SC & Feaster, DJ 2017, AAFA: Associative affinity factor analysis for bot detection and stance classification in Twitter. in Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017. vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 356-365, 18th IEEE International Conference on Information Reuse and Integration, IRI 2017, San Diego, United States, 8/4/17. https://doi.org/10.1109/IRI.2017.25
Sadiq S, Yan Y, Taylor A, Shyu M-L, Chen SC, Feaster DJ. AAFA: Associative affinity factor analysis for bot detection and stance classification in Twitter. In Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017. Vol. 2017-January. Institute of Electrical and Electronics Engineers Inc. 2017. p. 356-365 https://doi.org/10.1109/IRI.2017.25
Sadiq, Saad ; Yan, Yilin ; Taylor, Asia ; Shyu, Mei-Ling ; Chen, Shu Ching ; Feaster, Daniel J. / AAFA : Associative affinity factor analysis for bot detection and stance classification in Twitter. Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. pp. 356-365
@inproceedings{381a7726e3404dc5abd3411c65ce6392,
title = "AAFA: Associative affinity factor analysis for bot detection and stance classification in Twitter",
abstract = "The rise in popularity of social interacting websites such as Facebook, Twitter, and Snapchat has been challenged by the upsurge of unwelcomed and troubling bodies on these systems. This includes spam senders, malware systems, and other content contaminators. It is noted that highly automated accounts with 450 tweets per day produced almost 18{\%} of entire Twitter circulation in the 2016 U.S. Presidential election. It is also observed that those disruptive systems called bots are inclined more towards circulating negative news than positive information. This paper introduces a novel framework named Associative Affinity Factor Analysis (AAFA) designed for stance detection and bot identification. Using AAFA, the proposed framework identifies real people from bots and detects the stance in bipolar affinities. The 2016 U.S. Presidential election campaign was used as a test use case because of its significant and unique counter-factual properties. The results show that our proposed AAFA framework achieves high accuracy when compared to several existing state-of-theart methods.",
keywords = "Association affinity, Bot detection, Factor analysis, Stance classification",
author = "Saad Sadiq and Yilin Yan and Asia Taylor and Mei-Ling Shyu and Chen, {Shu Ching} and Feaster, {Daniel J}",
year = "2017",
month = "11",
day = "8",
doi = "10.1109/IRI.2017.25",
language = "English (US)",
volume = "2017-January",
pages = "356--365",
booktitle = "Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - AAFA

T2 - Associative affinity factor analysis for bot detection and stance classification in Twitter

AU - Sadiq, Saad

AU - Yan, Yilin

AU - Taylor, Asia

AU - Shyu, Mei-Ling

AU - Chen, Shu Ching

AU - Feaster, Daniel J

PY - 2017/11/8

Y1 - 2017/11/8

N2 - The rise in popularity of social interacting websites such as Facebook, Twitter, and Snapchat has been challenged by the upsurge of unwelcomed and troubling bodies on these systems. This includes spam senders, malware systems, and other content contaminators. It is noted that highly automated accounts with 450 tweets per day produced almost 18% of entire Twitter circulation in the 2016 U.S. Presidential election. It is also observed that those disruptive systems called bots are inclined more towards circulating negative news than positive information. This paper introduces a novel framework named Associative Affinity Factor Analysis (AAFA) designed for stance detection and bot identification. Using AAFA, the proposed framework identifies real people from bots and detects the stance in bipolar affinities. The 2016 U.S. Presidential election campaign was used as a test use case because of its significant and unique counter-factual properties. The results show that our proposed AAFA framework achieves high accuracy when compared to several existing state-of-theart methods.

AB - The rise in popularity of social interacting websites such as Facebook, Twitter, and Snapchat has been challenged by the upsurge of unwelcomed and troubling bodies on these systems. This includes spam senders, malware systems, and other content contaminators. It is noted that highly automated accounts with 450 tweets per day produced almost 18% of entire Twitter circulation in the 2016 U.S. Presidential election. It is also observed that those disruptive systems called bots are inclined more towards circulating negative news than positive information. This paper introduces a novel framework named Associative Affinity Factor Analysis (AAFA) designed for stance detection and bot identification. Using AAFA, the proposed framework identifies real people from bots and detects the stance in bipolar affinities. The 2016 U.S. Presidential election campaign was used as a test use case because of its significant and unique counter-factual properties. The results show that our proposed AAFA framework achieves high accuracy when compared to several existing state-of-theart methods.

KW - Association affinity

KW - Bot detection

KW - Factor analysis

KW - Stance classification

UR - http://www.scopus.com/inward/record.url?scp=85044219816&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044219816&partnerID=8YFLogxK

U2 - 10.1109/IRI.2017.25

DO - 10.1109/IRI.2017.25

M3 - Conference contribution

VL - 2017-January

SP - 356

EP - 365

BT - Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -