International Research Journal of Engineering and Technology (IRJET)
Volume: 13 Issue: 04 | Apr 2026
www.irjet.net
e-ISSN: 2395-0056 p-ISSN: 2395-0072
HateGuard: Automated Multi-Class Cyberbullying Detection Framework R.Lahari1, V.Munni2 1Pursuing Computer Science, Andhra Loyola Institute of Engineering and Technology, Vijayawada - 12 2AssociateProfessor,Department of CSE(AIML),Andhra Loyola Institute of Engineering and Technology,
Vijayawada – 12
---------------------------------------------------------------------***--------------------------------------------------------------------
ABSTRACT - The rapid growth of social media platforms
To address these challenges, there is a growing need for automated systems capable of accurately identifying and categorizing cyberbullying content in real time. Natural Language Processing (NLP) provides effective tools for analyzing textual data and extracting meaningful patterns that can be used for classification tasks. In this context, machine learning-based approaches have shown promise in detecting abusive language by learning from labeled datasets. However, many existing systems focus only on binary classification, failing to capture the nuanced differences between various types of cyberbullying.
has led to a significant increase in cyberbullying, posing serious challenges to user safety and online communication. Detecting and categorizing such harmful content at scale requires efficient and automated Natural Language Processing (NLP) techniques. This work presents a multi-class cyberbullying detection system designed to classify textual data from social media into six categories: age-based, ethnicity-based, gender-based, religion-based, other cyberbullying, and noncyberbullying. The proposed approach follows a structured pipeline involving text preprocessing techniques such as tokenization, stopword removal, and lemmatization using NLTK, followed by feature extraction using Term Frequency–Inverse Document Frequency (TFIDF). Multiple machine learning models, including Logistic Regression, Support Vector Machine (SVM), Random Forest, XGBoost, and Multinomial Naive Bayes, are trained and evaluated to determine the most effective classifier. Experimental results show that Logistic Regression achieves the best performance, with an accuracy of 81.9% and an F1-score of 0.822, demonstrating reliable classification across multiple categories.
This work aims to develop a multi-class classification system that can detect and categorize cyberbullying into six distinct classes: age-based, ethnicity-based, genderbased, religion-based, other cyberbullying, and noncyberbullying. By leveraging text preprocessing techniques, feature extraction methods, and multiple machine learning algorithms, the proposed system seeks to improve the accuracy and granularity of cyberbullying detection, thereby contributing to safer and more inclusive online environments.
Keywords- Cyberbullying detection, Natural Language Processing, text classification, TF-IDF, machine learning, Logistic Regression, Support Vector Machine, Random Forest, XGBoost, Naive Bayes, social media analysis, multi-class classification
I.
II. LITERATURE SURVEY Cyberbullying detection has been an active area of research within Natural Language Processing (NLP), with various approaches proposed to identify abusive and harmful content on online platforms. Early research primarily focused on traditional machine learning techniques combined with handcrafted features such as bag-of-words and Term Frequency–Inverse Document Frequency (TF-IDF) [15]. These approaches provided a foundation for automated text classification and were widely adopted due to their simplicity and computational efficiency [13].
INTRODUCTION
The rapid expansion of social media platforms has transformed the way individuals communicate, share opinions, and interact in digital spaces. While these platforms offer numerous benefits, they have also become a breeding ground for harmful behaviors such as cyberbullying, which can have serious psychological and social consequences for individuals. Cyberbullying manifests in various forms, including harassment based on age, gender, ethnicity, and religion, making its detection a complex and multi-dimensional problem. Traditional moderation techniques, which rely heavily on manual review, are not scalable given the vast volume of user-generated content produced across platforms.
© 2026, IRJET
|
Impact Factor value: 8.315
Algorithms such as Multinomial Naive Bayes and Support Vector Machine (SVM) were commonly used in these early systems and demonstrated reasonable performance in detecting offensive language [1], [2]. However, these models relied heavily on surface-level textual features and failed to capture deeper contextual meaning and semantic relationships. As a result, their effectiveness decreased when dealing with subtle,
|
ISO 9001:2008 Certified Journal
|
Page 1006