BotSpot: Deep learning classification of bot accounts within Twitter

Christopher Braker; Stavros Shiaeles; Gueltoum Bendiab; Nick Savage; Konstantinos Limniotis

doi:10.1007/978-3-030-65726-0_16

BotSpot: Deep learning classification of bot accounts within Twitter

Christopher Braker^*, Stavros Shiaeles, Gueltoum Bendiab, Nick Savage, Konstantinos Limniotis

^*Corresponding author for this work

School of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

375 Downloads (Pure)

Abstract

The openness feature of Twitter allows programs to generate and control Twitter accounts automatically via the Twitter API. These accounts, which are known as “bots”, can automatically perform actions such as tweeting, re-tweeting, following, unfollowing, or direct messaging other accounts, just like real people. They can also conduct malicious tasks such as spreading of fake news, spams, malicious software and other cyber-crimes. In this paper, we introduce a novel bot detection approach using deep learning, with the Multi-layer Perceptron Neural Networks and nine features of a bot account. A web crawler is developed to automatically collect data from public Twitter accounts and build the testing and training datasets, with 860 samples of human and bot accounts. After the initial training is done, the Multi-layer Perceptron Neural Networks achieved an overall accuracy rate of 92%, which proves the performance of the proposed approach.

Original language	English
Title of host publication	Internet of Things, Smart Spaces, and Next Generation Networks and Systems - 20th International Conference, NEW2AN 2020 and 13th Conference, ruSMART 2020, Proceedings
Editors	Olga Galinina, Sergey Andreev, Sergey Balandin, Yevgeni Koucheryavy
Publisher	Springer
Pages	165-175
Number of pages	11
ISBN (Electronic)	9783030657260
ISBN (Print)	9783030657253
DOIs	https://doi.org/10.1007/978-3-030-65726-0_16
Publication status	Published - 22 Dec 2020
Event	20th International Conference on Next Generation Teletraffic and Wired/Wireless Advanced Networks and Systems, NEW2AN 2020 and 13th Conference on the Internet of Things and Smart Spaces, ruSMART 2020 - St. Petersburg, Russian Federation Duration: 26 Aug 2020 → 28 Aug 2020

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	12525
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	20th International Conference on Next Generation Teletraffic and Wired/Wireless Advanced Networks and Systems, NEW2AN 2020 and 13th Conference on the Internet of Things and Smart Spaces, ruSMART 2020
Country/Territory	Russian Federation
City	St. Petersburg
Period	26/08/20 → 28/08/20

Keywords

Bot accounts
Machine learning
Security
Spam bots

UN SDGs

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

Access to Document

10.1007/978-3-030-65726-0_16

BotSpot AAM
This is a post-peer-review, pre-copyedit version of an article published in Lecture Notes in Computer Science. The final authenticated version is available online at: http://dx.doi.org/10.1007/978-3-030-65726-0_16.
Accepted author manuscript (Post-print), 939 KB

Cite this

Braker, C., Shiaeles, S., Bendiab, G., Savage, N., & Limniotis, K. (2020). BotSpot: Deep learning classification of bot accounts within Twitter. In O. Galinina, S. Andreev, S. Balandin, & Y. Koucheryavy (Eds.), Internet of Things, Smart Spaces, and Next Generation Networks and Systems - 20th International Conference, NEW2AN 2020 and 13th Conference, ruSMART 2020, Proceedings (pp. 165-175). (Lecture Notes in Computer Science; Vol. 12525). Springer. https://doi.org/10.1007/978-3-030-65726-0_16

Braker, Christopher ; Shiaeles, Stavros ; Bendiab, Gueltoum et al. / BotSpot : Deep learning classification of bot accounts within Twitter. Internet of Things, Smart Spaces, and Next Generation Networks and Systems - 20th International Conference, NEW2AN 2020 and 13th Conference, ruSMART 2020, Proceedings. editor / Olga Galinina ; Sergey Andreev ; Sergey Balandin ; Yevgeni Koucheryavy. Springer, 2020. pp. 165-175 (Lecture Notes in Computer Science).

@inproceedings{3456d29183d143e9b5b0e91f9d883498,

title = "BotSpot: Deep learning classification of bot accounts within Twitter",

abstract = "The openness feature of Twitter allows programs to generate and control Twitter accounts automatically via the Twitter API. These accounts, which are known as “bots”, can automatically perform actions such as tweeting, re-tweeting, following, unfollowing, or direct messaging other accounts, just like real people. They can also conduct malicious tasks such as spreading of fake news, spams, malicious software and other cyber-crimes. In this paper, we introduce a novel bot detection approach using deep learning, with the Multi-layer Perceptron Neural Networks and nine features of a bot account. A web crawler is developed to automatically collect data from public Twitter accounts and build the testing and training datasets, with 860 samples of human and bot accounts. After the initial training is done, the Multi-layer Perceptron Neural Networks achieved an overall accuracy rate of 92%, which proves the performance of the proposed approach.",

keywords = "Bot accounts, Machine learning, Security, Spam bots",

author = "Christopher Braker and Stavros Shiaeles and Gueltoum Bendiab and Nick Savage and Konstantinos Limniotis",

note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2020. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; 20th International Conference on Next Generation Teletraffic and Wired/Wireless Advanced Networks and Systems, NEW2AN 2020 and 13th Conference on the Internet of Things and Smart Spaces, ruSMART 2020 ; Conference date: 26-08-2020 Through 28-08-2020",

year = "2020",

month = dec,

day = "22",

doi = "10.1007/978-3-030-65726-0_16",

language = "English",

isbn = "9783030657253",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "165--175",

editor = "Olga Galinina and Sergey Andreev and Sergey Balandin and Yevgeni Koucheryavy",

booktitle = "Internet of Things, Smart Spaces, and Next Generation Networks and Systems - 20th International Conference, NEW2AN 2020 and 13th Conference, ruSMART 2020, Proceedings",

}

Braker, C, Shiaeles, S, Bendiab, G, Savage, N & Limniotis, K 2020, BotSpot: Deep learning classification of bot accounts within Twitter. in O Galinina, S Andreev, S Balandin & Y Koucheryavy (eds), Internet of Things, Smart Spaces, and Next Generation Networks and Systems - 20th International Conference, NEW2AN 2020 and 13th Conference, ruSMART 2020, Proceedings. Lecture Notes in Computer Science, vol. 12525, Springer, pp. 165-175, 20th International Conference on Next Generation Teletraffic and Wired/Wireless Advanced Networks and Systems, NEW2AN 2020 and 13th Conference on the Internet of Things and Smart Spaces, ruSMART 2020, St. Petersburg, Russian Federation, 26/08/20. https://doi.org/10.1007/978-3-030-65726-0_16

BotSpot: Deep learning classification of bot accounts within Twitter. / Braker, Christopher; Shiaeles, Stavros; Bendiab, Gueltoum et al.
Internet of Things, Smart Spaces, and Next Generation Networks and Systems - 20th International Conference, NEW2AN 2020 and 13th Conference, ruSMART 2020, Proceedings. ed. / Olga Galinina; Sergey Andreev; Sergey Balandin; Yevgeni Koucheryavy. Springer, 2020. p. 165-175 (Lecture Notes in Computer Science; Vol. 12525).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - BotSpot

T2 - 20th International Conference on Next Generation Teletraffic and Wired/Wireless Advanced Networks and Systems, NEW2AN 2020 and 13th Conference on the Internet of Things and Smart Spaces, ruSMART 2020

AU - Braker, Christopher

AU - Shiaeles, Stavros

AU - Bendiab, Gueltoum

AU - Savage, Nick

AU - Limniotis, Konstantinos

PY - 2020/12/22

Y1 - 2020/12/22

N2 - The openness feature of Twitter allows programs to generate and control Twitter accounts automatically via the Twitter API. These accounts, which are known as “bots”, can automatically perform actions such as tweeting, re-tweeting, following, unfollowing, or direct messaging other accounts, just like real people. They can also conduct malicious tasks such as spreading of fake news, spams, malicious software and other cyber-crimes. In this paper, we introduce a novel bot detection approach using deep learning, with the Multi-layer Perceptron Neural Networks and nine features of a bot account. A web crawler is developed to automatically collect data from public Twitter accounts and build the testing and training datasets, with 860 samples of human and bot accounts. After the initial training is done, the Multi-layer Perceptron Neural Networks achieved an overall accuracy rate of 92%, which proves the performance of the proposed approach.

AB - The openness feature of Twitter allows programs to generate and control Twitter accounts automatically via the Twitter API. These accounts, which are known as “bots”, can automatically perform actions such as tweeting, re-tweeting, following, unfollowing, or direct messaging other accounts, just like real people. They can also conduct malicious tasks such as spreading of fake news, spams, malicious software and other cyber-crimes. In this paper, we introduce a novel bot detection approach using deep learning, with the Multi-layer Perceptron Neural Networks and nine features of a bot account. A web crawler is developed to automatically collect data from public Twitter accounts and build the testing and training datasets, with 860 samples of human and bot accounts. After the initial training is done, the Multi-layer Perceptron Neural Networks achieved an overall accuracy rate of 92%, which proves the performance of the proposed approach.

KW - Bot accounts

KW - Machine learning

KW - Security

KW - Spam bots

UR - http://www.scopus.com/inward/record.url?scp=85101961306&partnerID=8YFLogxK

UR - http://www.new2an.org/#/

U2 - 10.1007/978-3-030-65726-0_16

DO - 10.1007/978-3-030-65726-0_16

M3 - Conference contribution

AN - SCOPUS:85101961306

SN - 9783030657253

T3 - Lecture Notes in Computer Science

SP - 165

EP - 175

BT - Internet of Things, Smart Spaces, and Next Generation Networks and Systems - 20th International Conference, NEW2AN 2020 and 13th Conference, ruSMART 2020, Proceedings

A2 - Galinina, Olga

A2 - Andreev, Sergey

A2 - Balandin, Sergey

A2 - Koucheryavy, Yevgeni

PB - Springer

Y2 - 26 August 2020 through 28 August 2020

ER -

Braker C, Shiaeles S, Bendiab G, Savage N, Limniotis K. BotSpot: Deep learning classification of bot accounts within Twitter. In Galinina O, Andreev S, Balandin S, Koucheryavy Y, editors, Internet of Things, Smart Spaces, and Next Generation Networks and Systems - 20th International Conference, NEW2AN 2020 and 13th Conference, ruSMART 2020, Proceedings. Springer. 2020. p. 165-175. (Lecture Notes in Computer Science). doi: 10.1007/978-3-030-65726-0_16

BotSpot: Deep learning classification of bot accounts within Twitter

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this