On mission Twitter profiles: a study of selective toxic behavior

Hina Qayyum; Muhammad Ikram; Benjamin Zi Hao Zhao; Ian D. Wood; Nicolas Kourtellis; Mohamed Ali Kaafar

doi:10.1109/BigData59044.2023.10386248

On mission Twitter profiles: a study of selective toxic behavior

Hina Qayyum^*, Muhammad Ikram, Benjamin Zi Hao Zhao, Ian D. Wood, Nicolas Kourtellis, Mohamed Ali Kaafar

^*Corresponding author for this work

School of Computing

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

Abstract

The argument for persistent social media influence campaigns, often funded by malicious entities, is gaining traction. These entities utilize instrumented profiles to disseminate divisive content and disinformation, shaping public perception. Despite ample evidence of these instrumented profiles, few identification methods exist to locate them in the wild. To evade detection and appear genuine, small clusters of instrumented profiles engage in unrelated discussions, diverting attention from their true goals [34]. This strategic thematic diversity conceals their selective polarity towards certain topics and fosters public trust [49].

This study aims to characterize profiles potentially used for influence operations, termed 'on-mission profiles,' relying solely on thematic content diversity within unlabeled data. Distinguishing this work is its focus on content volume and toxicity towards specific themes. Longitudinal data from 138K Twitter (rebranded as X) profiles and 293M tweets enables profiling based on theme diversity. High thematic diversity groups predominantly produce toxic content concerning specific themes, like politics, health, and news - classifying them as 'on-mission' profiles.

Using the identified on-mission' profiles, we design a classifier for unseen, unlabeled data. Employing a linear SVM model, we train and test it on an 80/20% split of the most diverse profiles. The classifier achieves a flawless 100% accuracy, facilitating the discovery of previously unknown 'on-mission' profiles in the wild.

Original language	English
Title of host publication	2023 IEEE International Conference on Big Data
Subtitle of host publication	proceedings
Editors	Jingrui He, Themis Palpanas, Xiaohua Hu, Alfredo Cuzzocrea, Dejing Dou, Dominik Slezak, Wei Wang, Aleksandra Gruca, Jerry Chun-Wei Lin, Rakesh Agrawal
Place of Publication	Piscataway, NJ
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	3634-3643
Number of pages	10
ISBN (Electronic)	9798350324457
ISBN (Print)	9798350324464
DOIs	https://doi.org/10.1109/BigData59044.2023.10386248
Publication status	Published - 2023
Event	2023 IEEE International Conference on Big Data, BigData 2023 - Sorrento, Italy Duration: 15 Dec 2023 → 18 Dec 2023

Conference

Conference	2023 IEEE International Conference on Big Data, BigData 2023
Country/Territory	Italy
City	Sorrento
Period	15/12/23 → 18/12/23

Access to Document

10.1109/BigData59044.2023.10386248

Cite this

Qayyum, H., Ikram, M., Zhao, B. Z. H., Wood, I. D., Kourtellis, N., & Kaafar, M. A. (2023). On mission Twitter profiles: a study of selective toxic behavior. In J. He, T. Palpanas, X. Hu, A. Cuzzocrea, D. Dou, D. Slezak, W. Wang, A. Gruca, J. C.-W. Lin, & R. Agrawal (Eds.), 2023 IEEE International Conference on Big Data: proceedings (pp. 3634-3643). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/BigData59044.2023.10386248

Qayyum, Hina ; Ikram, Muhammad ; Zhao, Benjamin Zi Hao et al. / On mission Twitter profiles : a study of selective toxic behavior. 2023 IEEE International Conference on Big Data: proceedings. editor / Jingrui He ; Themis Palpanas ; Xiaohua Hu ; Alfredo Cuzzocrea ; Dejing Dou ; Dominik Slezak ; Wei Wang ; Aleksandra Gruca ; Jerry Chun-Wei Lin ; Rakesh Agrawal. Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE), 2023. pp. 3634-3643

@inproceedings{2435575a35f14c18b1c07384f1644ef2,

title = "On mission Twitter profiles: a study of selective toxic behavior",

abstract = "The argument for persistent social media influence campaigns, often funded by malicious entities, is gaining traction. These entities utilize instrumented profiles to disseminate divisive content and disinformation, shaping public perception. Despite ample evidence of these instrumented profiles, few identification methods exist to locate them in the wild. To evade detection and appear genuine, small clusters of instrumented profiles engage in unrelated discussions, diverting attention from their true goals [34]. This strategic thematic diversity conceals their selective polarity towards certain topics and fosters public trust [49]. This study aims to characterize profiles potentially used for influence operations, termed 'on-mission profiles,' relying solely on thematic content diversity within unlabeled data. Distinguishing this work is its focus on content volume and toxicity towards specific themes. Longitudinal data from 138K Twitter (rebranded as X) profiles and 293M tweets enables profiling based on theme diversity. High thematic diversity groups predominantly produce toxic content concerning specific themes, like politics, health, and news - classifying them as 'on-mission' profiles. Using the identified on-mission' profiles, we design a classifier for unseen, unlabeled data. Employing a linear SVM model, we train and test it on an 80/20% split of the most diverse profiles. The classifier achieves a flawless 100% accuracy, facilitating the discovery of previously unknown 'on-mission' profiles in the wild.",

author = "Hina Qayyum and Muhammad Ikram and Zhao, {Benjamin Zi Hao} and Wood, {Ian D.} and Nicolas Kourtellis and Kaafar, {Mohamed Ali}",

year = "2023",

doi = "10.1109/BigData59044.2023.10386248",

language = "English",

isbn = "9798350324464",

pages = "3634--3643",

editor = "Jingrui He and Themis Palpanas and Xiaohua Hu and Alfredo Cuzzocrea and Dejing Dou and Dominik Slezak and Wei Wang and Aleksandra Gruca and Lin, {Jerry Chun-Wei} and Rakesh Agrawal",

booktitle = "2023 IEEE International Conference on Big Data",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "2023 IEEE International Conference on Big Data, BigData 2023 ; Conference date: 15-12-2023 Through 18-12-2023",

}

Qayyum, H, Ikram, M, Zhao, BZH, Wood, ID, Kourtellis, N & Kaafar, MA 2023, On mission Twitter profiles: a study of selective toxic behavior. in J He, T Palpanas, X Hu, A Cuzzocrea, D Dou, D Slezak, W Wang, A Gruca, JC-W Lin & R Agrawal (eds), 2023 IEEE International Conference on Big Data: proceedings. Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, pp. 3634-3643, 2023 IEEE International Conference on Big Data, BigData 2023, Sorrento, Italy, 15/12/23. https://doi.org/10.1109/BigData59044.2023.10386248

On mission Twitter profiles: a study of selective toxic behavior. / Qayyum, Hina; Ikram, Muhammad; Zhao, Benjamin Zi Hao et al.
2023 IEEE International Conference on Big Data: proceedings. ed. / Jingrui He; Themis Palpanas; Xiaohua Hu; Alfredo Cuzzocrea; Dejing Dou; Dominik Slezak; Wei Wang; Aleksandra Gruca; Jerry Chun-Wei Lin; Rakesh Agrawal. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2023. p. 3634-3643.

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

TY - GEN

T1 - On mission Twitter profiles

T2 - 2023 IEEE International Conference on Big Data, BigData 2023

AU - Qayyum, Hina

AU - Ikram, Muhammad

AU - Zhao, Benjamin Zi Hao

AU - Wood, Ian D.

AU - Kourtellis, Nicolas

AU - Kaafar, Mohamed Ali

PY - 2023

Y1 - 2023

N2 - The argument for persistent social media influence campaigns, often funded by malicious entities, is gaining traction. These entities utilize instrumented profiles to disseminate divisive content and disinformation, shaping public perception. Despite ample evidence of these instrumented profiles, few identification methods exist to locate them in the wild. To evade detection and appear genuine, small clusters of instrumented profiles engage in unrelated discussions, diverting attention from their true goals [34]. This strategic thematic diversity conceals their selective polarity towards certain topics and fosters public trust [49]. This study aims to characterize profiles potentially used for influence operations, termed 'on-mission profiles,' relying solely on thematic content diversity within unlabeled data. Distinguishing this work is its focus on content volume and toxicity towards specific themes. Longitudinal data from 138K Twitter (rebranded as X) profiles and 293M tweets enables profiling based on theme diversity. High thematic diversity groups predominantly produce toxic content concerning specific themes, like politics, health, and news - classifying them as 'on-mission' profiles. Using the identified on-mission' profiles, we design a classifier for unseen, unlabeled data. Employing a linear SVM model, we train and test it on an 80/20% split of the most diverse profiles. The classifier achieves a flawless 100% accuracy, facilitating the discovery of previously unknown 'on-mission' profiles in the wild.

AB - The argument for persistent social media influence campaigns, often funded by malicious entities, is gaining traction. These entities utilize instrumented profiles to disseminate divisive content and disinformation, shaping public perception. Despite ample evidence of these instrumented profiles, few identification methods exist to locate them in the wild. To evade detection and appear genuine, small clusters of instrumented profiles engage in unrelated discussions, diverting attention from their true goals [34]. This strategic thematic diversity conceals their selective polarity towards certain topics and fosters public trust [49]. This study aims to characterize profiles potentially used for influence operations, termed 'on-mission profiles,' relying solely on thematic content diversity within unlabeled data. Distinguishing this work is its focus on content volume and toxicity towards specific themes. Longitudinal data from 138K Twitter (rebranded as X) profiles and 293M tweets enables profiling based on theme diversity. High thematic diversity groups predominantly produce toxic content concerning specific themes, like politics, health, and news - classifying them as 'on-mission' profiles. Using the identified on-mission' profiles, we design a classifier for unseen, unlabeled data. Employing a linear SVM model, we train and test it on an 80/20% split of the most diverse profiles. The classifier achieves a flawless 100% accuracy, facilitating the discovery of previously unknown 'on-mission' profiles in the wild.

UR - http://www.scopus.com/inward/record.url?scp=85184987399&partnerID=8YFLogxK

U2 - 10.1109/BigData59044.2023.10386248

DO - 10.1109/BigData59044.2023.10386248

M3 - Conference proceeding contribution

AN - SCOPUS:85184987399

SN - 9798350324464

SP - 3634

EP - 3643

BT - 2023 IEEE International Conference on Big Data

A2 - He, Jingrui

A2 - Palpanas, Themis

A2 - Hu, Xiaohua

A2 - Cuzzocrea, Alfredo

A2 - Dou, Dejing

A2 - Slezak, Dominik

A2 - Wang, Wei

A2 - Gruca, Aleksandra

A2 - Lin, Jerry Chun-Wei

A2 - Agrawal, Rakesh

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ

Y2 - 15 December 2023 through 18 December 2023

ER -

Qayyum H, Ikram M, Zhao BZH, Wood ID, Kourtellis N, Kaafar MA. On mission Twitter profiles: a study of selective toxic behavior. In He J, Palpanas T, Hu X, Cuzzocrea A, Dou D, Slezak D, Wang W, Gruca A, Lin JCW, Agrawal R, editors, 2023 IEEE International Conference on Big Data: proceedings. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). 2023. p. 3634-3643 doi: 10.1109/BigData59044.2023.10386248

On mission Twitter profiles: a study of selective toxic behavior

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this