A Machine Learning Ensemble Model for the Detection of Cyberbullying - Stacking Ensemble - Automated Aggressive Tweet Classification

Aug 2, 2026

Upload by Maeve

The pervasive use of social media platforms has expanded connectivity while simultaneously increasing cyberbullying through anonymity and easy, constant access. Detecting, monitoring, and mitigating aggressive posts is therefore essential for protecting users’ emotional well-being. This study proposes an automated binary-labeling system for aggressive tweets using a stacking ensemble machine learning approach with multiple feature-extraction techniques. Five algorithms are combined, achieving 94.00% accuracy on the same dataset.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Abstract

Introduction

Motivation and background

Challenges in cyberbullying detection

NLP and machine learning approaches

A MACHINE LEARNING ENSEMBLE MODEL FOR THE DETECTION OF CYBERBULLYING Abulkarim Faraj Alqahtani 1, 2 and Mohammad Ilyas 1 1Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, USA 2Ministry of National Guard, King Khalid Military Academy, Riyadh 14625, Saudi Arabia ABSTRACT The pervasive use of social media platforms, such as Facebook, Instagram, and X, has significantly amplified our electronic interconnectedness. Moreover, these platforms are now easily accessible from any location at any given time. However, the increased popularity of social media has also led to cyberbullying.It is imperative to address the need for finding, monitoring, and mitigating cyberbullying posts on social media platforms. Motivated by this necessity, we present this paper to contribute to developing an automated system for detecting binary labels of aggressive tweets. Our study has demonstrated remarkable performance compared to previous experiments on the same dataset. We employed the stacking ensemble machine learning method, utilizing four various feature extraction techniques to optimize performance within the stacking ensemble learning framework. Combining five machine learning algorithms,Decision Trees, Random Forest, Linear Support Vector Classification, Logistic Regression, and K-Nearest Neighbors into an ensemble method, we achieved superior results compared to traditional machine learning classifier models. The stacking classifier achieved a high accuracy rate of 94. 00%, outperforming traditional machine learning models and surpassing the results of prior experiments that utilized the same dataset. The outcomes of our experiments showcased an accuracy rate of 0.94% in detection tweets as aggressive or non-aggressive. KEYWORDS Machine Learning, Stacking Ensemble Learning, Cyberbullying Detection,Stacking Classifier, Feature Extractions, Classification Time. 1. INTRODUCTION Today, social networking sites play a significant role in our daily lives. We use social media for various communications, encompassing entertainment, education, personal development, and the workplace. The revolutionary nature of these platforms has made it much easier to connect with people across long distances [1] . Individuals access social media platforms on their cellphones, tablets, and smartwatches, thanks to the widespread and rapid expansion of the internet. Technological advancements have transformed the way we communicate, share information, and interact with communities globally [2] . While social media has many beneficial aspects, it can also be misused. Social media platforms allow users to remain anonymous and conceal their identities, enabling some individuals to abuse these technical capabilities. Bullying, especially cyberbullying, tends to escalate with increased frequency over time. Moreover, the anonymity feature emboldens people to make harsh comments and engage in cyberbullying [3] . The authors in [4] emphasize that cyberbullying profoundly impacts the emotional and psychological well-being of victims. Their study reveals an alarming increase in the frequency of cyberbullying, particularly among teenagers, highlighting it as a significant concern. The authors identify social platforms where cyberbullying occurs, such as X, Facebook, and email. The absence of age restrictions on many social media networks is flagged as a harmful policy with a chilling effect on youths [5] . The misuse of these platforms not only contributes to cyberbullying but also fosters other antisocial acts, rendering them potentially unsafe even for adults. Thus, cyberbullying poses a universal threat, affecting individuals of all ages and locations [6] . Disagreements in viewpoints can escalate into bullying behaviors, defined as aggressive interactions involving words, texts, or tweets between two or more individuals [7] . Those unfamiliar with the benefits of social media may resort to threateni

FAQs

Why is cyberbullying detection important on social media platforms?

Social media use has increased anonymity and the frequency of harmful behaviors. Cyberbullying can seriously affect victims’ emotional and psychological well-being, making detection and mitigation necessary.

What approach does the study use to detect cyberbullying?

The study uses a stacking ensemble machine learning method. It combines five algorithms and employs four feature extraction techniques within the stacking framework.

How effective is the proposed model compared with prior work?

The stacking classifier achieves 94.00% accuracy on the same dataset. It outperforms traditional machine learning classifiers and earlier experiments reported for that dataset.

Aug 2, 2026

Upload by Maeve