Power of Social Media Meta Data: Enhancing Cyberbullying Detection

Tasmina Islam; Zhou Zhou

doi:10.1007/978-3-031-82031-1_19

Power of Social Media Meta Data: Enhancing Cyberbullying Detection

Tasmina Islam, Zhou Zhou

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

19 Downloads (Pure)

Abstract

Cyberbullying poses a significant challenge in today’s digital society due to its widespread reach and persistent effects. This paper investigates the role of metadata in enhancing cyberbullying detection across three datasets from YouTube, Twitter, and Sina Weibo. Using Correlation-Based Feature Selection and machine learning classifiers (Naive Bayes, Random Forest, and Bagging), the impact of user and social media meta-features on detection performance is analysed. The results show that while user metadata had minimal influence on detection accuracy, social media metadata, particularly, Retweets, Favourites, and SenderFollowers, significantly improved detection performance, enhancing accuracy by up to 9.7%.

Original language	English
Title of host publication	Cybersecurity and Human Capabilities Through Symbiotic Artificial Intelligence
Pages	339–361
Number of pages	23
DOIs	https://doi.org/10.1007/978-3-031-82031-1_19
Publication status	Published - 14 May 2025

Publication series

Name	Advanced Sciences and Technologies for Security Applications
Volume	Part F414
ISSN (Print)	1613-5113
ISSN (Electronic)	2363-9466

UN SDGs

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

Access to Document

10.1007/978-3-031-82031-1_19

ICGS3-24-Cyberbullying- preprintAccepted author manuscript, 413 KB

Cite this

@inbook{ee2271c76f2c4c8e8c4392b1c5f66967,

title = "Power of Social Media Meta Data: Enhancing Cyberbullying Detection",

abstract = "Cyberbullying poses a significant challenge in today{\textquoteright}s digital society due to its widespread reach and persistent effects. This paper investigates the role of metadata in enhancing cyberbullying detection across three datasets from YouTube, Twitter, and Sina Weibo. Using Correlation-Based Feature Selection and machine learning classifiers (Naive Bayes, Random Forest, and Bagging), the impact of user and social media meta-features on detection performance is analysed. The results show that while user metadata had minimal influence on detection accuracy, social media metadata, particularly, Retweets, Favourites, and SenderFollowers, significantly improved detection performance, enhancing accuracy by up to 9.7%.",

author = "Tasmina Islam and Zhou Zhou",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.",

year = "2025",

month = may,

day = "14",

doi = "10.1007/978-3-031-82031-1_19",

language = "English",

series = "Advanced Sciences and Technologies for Security Applications",

pages = "339–361",

booktitle = "Cybersecurity and Human Capabilities Through Symbiotic Artificial Intelligence",

}

Power of Social Media Meta Data: Enhancing Cyberbullying Detection. / Islam, Tasmina; Zhou, Zhou.
Cybersecurity and Human Capabilities Through Symbiotic Artificial Intelligence. 2025. p. 339–361 (Advanced Sciences and Technologies for Security Applications; Vol. Part F414).

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

TY - CHAP

T1 - Power of Social Media Meta Data: Enhancing Cyberbullying Detection

AU - Islam, Tasmina

AU - Zhou, Zhou

PY - 2025/5/14

Y1 - 2025/5/14

N2 - Cyberbullying poses a significant challenge in today’s digital society due to its widespread reach and persistent effects. This paper investigates the role of metadata in enhancing cyberbullying detection across three datasets from YouTube, Twitter, and Sina Weibo. Using Correlation-Based Feature Selection and machine learning classifiers (Naive Bayes, Random Forest, and Bagging), the impact of user and social media meta-features on detection performance is analysed. The results show that while user metadata had minimal influence on detection accuracy, social media metadata, particularly, Retweets, Favourites, and SenderFollowers, significantly improved detection performance, enhancing accuracy by up to 9.7%.

AB - Cyberbullying poses a significant challenge in today’s digital society due to its widespread reach and persistent effects. This paper investigates the role of metadata in enhancing cyberbullying detection across three datasets from YouTube, Twitter, and Sina Weibo. Using Correlation-Based Feature Selection and machine learning classifiers (Naive Bayes, Random Forest, and Bagging), the impact of user and social media meta-features on detection performance is analysed. The results show that while user metadata had minimal influence on detection accuracy, social media metadata, particularly, Retweets, Favourites, and SenderFollowers, significantly improved detection performance, enhancing accuracy by up to 9.7%.

UR - http://www.scopus.com/inward/record.url?scp=105006938278&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-82031-1_19

DO - 10.1007/978-3-031-82031-1_19

M3 - Conference paper

T3 - Advanced Sciences and Technologies for Security Applications

SP - 339

EP - 361

BT - Cybersecurity and Human Capabilities Through Symbiotic Artificial Intelligence

ER -

Power of Social Media Meta Data: Enhancing Cyberbullying Detection

Abstract

Publication series

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this