Abstract :

The Rapid Rise Of Social Media Platforms Has Transformed How Young People Communicate And Interact, But It Has Also Given Rise To New Challenges Such As Cyberbullying — The Use Of Digital Technologies To Harass, Threaten, Or Humiliate Others. Cyberbullying Has Severe Psychological And Emotional Effects, Particularly Among Teenagers, Leading To Anxiety, Depression, And In Extreme Cases, Suicidal Tendencies. This Work Proposes A Machine Learning-based Cyberbullying Detection System That Leverages Natural Language Processing (NLP) Techniques To Automatically Identify And Classify Bullying-related Content On Social Networks. By Analyzing Text Patterns, Sentiment, And Linguistic Features, The System Can Distinguish Between Normal Conversations And Harmful Or Abusive Messages. Various Supervised Learning Algorithms Such As Support Vector Machines (SVM), Random Forest, And Logistic Regression Are Employed To Train Models On Labeled Datasets Containing Bullying And Non-bullying Content. The Proposed Approach Aims Not Only To Detect Abusive Language But Also To Consider Contextual Dependencies To Identify Ongoing Harassment Or Targeted Attacks. Experimental Results Demonstrate That The Integration Of NLP With Supervised Machine Learning Significantly Enhances The Accuracy Of Cyberbullying Detection, Offering A Valuable Tool For Safer And More Responsible Use Of Online Social Platforms. Index Terms — Cyberbullying Detection, Machine Learning, Natural Language Processing (NLP), Supervised Learning, Social Media Analysis, Text Classification, Sentiment Analysis, Online Harassment, Support Vector Machine (SVM), Random Forest, Logistic Regression.

Published:

29-10-2025

Issue:

Vol. 25 No. 10 (2025)

Page Nos:

354-362

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite