What is the Social Media Cyberbullying Detection System?

It is a machine learning-based system that detects cyberbullying content on social media platforms using text analysis and metadata features. It helps identify gender-based, religious, racial, sexual orientation, age-based, and ethnic bullying to foster safer online communities.

Which algorithms are used in this cyberbullying detection project?

The system implements and compares two classification algorithms: Random Forest and Logistic Regression. Random Forest achieved the best performance with 88.4% accuracy and an F1-score of 0.892.

What is the accuracy of this cyberbullying detection model?

The Random Forest model achieves 88.4% test accuracy with precision of 88.5%, recall of 88.4%, F1-score of 0.892, and ROC-AUC of 0.923, making it highly reliable for content moderation.

Who can benefit from this cyberbullying detection system?

Social media platforms can use it for content moderation, online communities for user protection, schools for student monitoring, researchers for studying online behavior, and NGOs for digital safety advocacy.

What technologies are used to build this project?

The project is built using Python with Pandas, NumPy, Scikit-learn, imbalanced-learn (SMOTE), NLTK, Matplotlib, and Seaborn for machine learning and NLP. The web interface is developed using Flask with HTML, CSS, and JavaScript.

Watch Demo Video

Machine Learning

Social Media Cyberbullying Detection Using Machine Learning

The Social Media Cyberbullying Detection Using Machine Learning system is a comprehensive machine learning solution that detects cyberbullying content on social media platforms using text analysis and metadata features. This project is ideal for B.Tech, MCA, CSE, and engineering students as their final year project. It uses advanced algorithms like Random Forest and Logistic Regression with SMOTE to achieve 88.4% accuracy.

The system leverages TF-IDF textual features combined with metadata features including word count, character count, hashtag count, mention count, and linguistic indicators. It provides interactive visualizations, feature importance analysis, model comparison, and real-time cyberbullying detection to help social media platforms and online communities foster safer digital spaces.

Python 3.8+ Machine Learning NLP Random Forest Logistic Regression TF-IDF SMOTE Scikit-learn NLTK Pandas NumPy Matplotlib Seaborn Flask HTML/CSS/JS

Key Features:

Multi-Category Cyberbullying Detection
Random Forest (88.4% Accuracy)
Logistic Regression (82.6% Accuracy)
TF-IDF + Metadata Feature Engineering
SMOTE for Class Imbalance
Feature Importance Analysis
Real-time Content Prediction
Model Performance Comparison
5-Fold Cross-Validation
Flask Web Application

Algorithms Used

🌲 Random Forest Classifier

Ensemble learning with 80 trees, handles high-dimensional text features effectively

🎯 Accuracy: 88.4%

📊 Logistic Regression

Linear model with L2 regularization, interpretable coefficients

🎯 Accuracy: 82.6%

📝 TF-IDF Vectorizer

Text feature extraction with n-gram support (1-2 grams)

📊 Features: 5,000+

🔍 5-Fold CV

Cross-validation for model stability and generalization

📊 RF: 0.923 ± 0.0045

Methodology & Workflow

1 Data Loading & Inspection
Social media dataset with 42,120 labeled tweets

2 Text Preprocessing
Cleaning, normalization, stopword removal, tokenization

3 Feature Engineering
TF-IDF vectors + metadata features (word count, hashtags, mentions)

4 Model Training
Random Forest & Logistic Regression with SMOTE

5 Model Evaluation
Accuracy, Precision, Recall, F1-Score, ROC-AUC, 5-fold CV

6 Web Deployment
Flask web app for real-time cyberbullying detection

Model Performance Comparison

Metric	Random Forest	Logistic Regression	Best
Accuracy	0.884	0.826	Random Forest
Precision	0.885	0.830	Random Forest
Recall	0.884	0.826	Random Forest
F1-Score	0.892	0.831	Random Forest
ROC-AUC	0.923	0.874	Random Forest
CV Mean (5-Fold)	0.923	0.874	Random Forest

Project Package Includes:

Complete Source Code Documentation (50+ pages) Video Tutorial Dataset (42,120 tweets) Flask Web App Model Files (Pickle) Visualizations 24/7 Expert Support

Check Payment Status

LIMITED TIME OFFER -70%

Complete Project Package Lifetime Access

Original Price

₹9,999

Today's Price ₹2,999 💎 Save ₹7,000

You Save ₹7,000 (70% OFF)

Complete Source Code

Documentation & PPT

Video Tutorial

24/7 Expert Support

Scan & Pay with UPI

SECURE

Payee Thirumalai Kumar

UPI ID 9600095045@icici

Amount ₹2,999

Submit Your Payment

100% SECURE

Full Name *

Email *

Phone Number *

College/University *

Degree

Passout Year

Department

Payment Details

Enter your UPI Transaction ID and upload payment screenshot for verification.

Transaction ID *

Payment Screenshot *

Click to upload screenshot JPG, PNG, GIF, PDF • Max 5MB

📚 Academic & Research Support Services

Need help with Thesis, Dissertation, Assignments, or PhD Research? We've got you covered!

📝

Thesis & Dissertation

Complete thesis writing, research guidance, and formatting support

Expert Help

📄

Assignment Help

Quality assignment writing, editing, and proofreading services

100% Original

🔬

PhD Research

Research proposal, literature review, data analysis & publication

PhD Level

📊

Project Guidance

Academic projects, mini projects, and final year project support

Hands-on

📞 Need custom support? Contact us directly!

Chat on WhatsApp → Email Us

Final Year Projects