Scribd
Upload
198 views2 pages

Cyberbullying Detection IEEE

This paper introduces a cyberbullying detection system that utilizes machine learning and natural language processing to identify harmful content on social media. The system aims to enhance online safety by classifying posts as harmful or benign, and it addresses challenges such as language diversity and real-time detection. Future improvements will focus on multilingual support and monitoring capabilities.

Uploaded by

Prem Dubay 3229
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
198 views2 pages

Cyberbullying Detection IEEE

This paper introduces a cyberbullying detection system that utilizes machine learning and natural language processing to identify harmful content on social media. The system aims to enhance online safety by classifying posts as harmful or benign, and it addresses challenges such as language diversity and real-time detection. Future improvements will focus on multilingual support and monitoring capabilities.

Uploaded by

Prem Dubay 3229
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Cyberbullying Detection System on Social Media

Sonu Prajapati, Sohum Patil, Buddhabhusan Waghmare

New Horizon Institute of Technology and Management, Thane

Abstract
This paper presents a cyberbullying detection system designed to identify and mitigate
instances of cyberbullying on social media platforms using machine learning algorithms. By
leveraging natural language processing and sentiment analysis, our system classifies posts
as harmful or benign, aiding platforms in real-time intervention. The proposed approach
aims to enhance online safety and support mental well-being among users.

Keywords
Cyberbullying, Machine Learning, Social Media, Sentiment Analysis, NLP

I. Introduction
A Cyberbullying Detection System for social media is designed to identify and mitigate
instances of online harassment. It employs machine learning algorithms and NLP
techniques to analyze user-generated content for harmful behavior, promoting a safer
online environment.

II. Literature Review


Several studies have proposed various machine learning approaches for detecting
cyberbullying. Techniques such as Support Vector Machines, Random Forests, and Neural
Networks have shown promising results in identifying harmful content.

III. Research Gaps


Existing cyberbullying detection systems face challenges such as language diversity,
evolving slang, privacy concerns, and real-time detection delays, which limit their
effectiveness.

IV. Proposed System


Our system collects data from social media, preprocesses text, extracts features using TF-
IDF and word embeddings, and classifies content using a hybrid machine learning approach.
Sentiment analysis further enhances detection accuracy.
V. Experimental Setup
We use datasets from platforms like Twitter and Facebook, applying machine learning
models such as SVM and BERT. The system is evaluated using accuracy, precision, recall,
and F1-score.

VI. Conclusion
Our system effectively detects cyberbullying instances with high accuracy. Future work will
focus on improving multilingual support and real-time monitoring capabilities.

References
[1] 2024 Cyberbullying Trends and Detection Technologies, Pew Research Center, 2024.

[2] T. Johnson, 'Enhanced Cyberbullying Detection on Social Media Platforms,' 2024.

[3] J. Smith, A. Lee, 'Advancements in Cyberbullying Detection: A Machine Learning


Approach,' 2024.

[4] R. Muneer, J. Shuja, S. Mahmood, 'Cyberbullying Detection using Deep Learning,' 2023.

You might also like