Scribd
Upload
14 views

Detection oof cyber bullying in social media using machine learningppt

The document presents a study on detecting cyberbullying on social media using machine learning and natural language processing, highlighting its impact on individuals and the need for effective regulation. It discusses existing systems, their limitations, and proposes an enhanced system with a comprehensive User Module for better monitoring and intervention. The proposed architecture aims to improve detection accuracy and create a safer online environment while addressing challenges like scalability and false positives.

Uploaded by

SAI POLAM
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
14 views

Detection oof cyber bullying in social media using machine learningppt

The document presents a study on detecting cyberbullying on social media using machine learning and natural language processing, highlighting its impact on individuals and the need for effective regulation. It discusses existing systems, their limitations, and proposes an enhanced system with a comprehensive User Module for better monitoring and intervention. The proposed architecture aims to improve detection accuracy and create a safer online environment while addressing challenges like scalability and false positives.

Uploaded by

SAI POLAM
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 19

Department : Computer Science and Engineering

Detection of Cyberbullying on Social Media Using


Machine Learning
Batch no:-9
Under the Guidance of Presented by
Mr. G.Chandra Sekhar M.Tech R.Harini Kusuma Priya 216M1A05A9
Assistant Professor P.Sai 216M1A05A0

P.Aswini Datta 216M1A0593


M.Madhuri 216M1A0570
ABSTRACT
Cyberbullying is a major problem encountered on internet that affects teenagers and also
adults. It has led to mis happenings like suicide and depression. Regulation of content on
social media platforms has become a growing need. The following study uses data from
two different forms of cyberbullying, hate speech tweets from Twitter and comments based
on personal attacks from Wikipedia forums to build a model based on detection of
Cyberbullying in text data using Natural Language Processing and Machine learning.
Three methods for Feature extraction and four classifiers are studied to outline the best
approach. For Tweet data the model provides accuracies above 90% and for Wikipedia
data it gives accuracies above 80%.
INTRODUCTION

Cyberbullying has become a growing concern in the digital era, where social media
platforms serve as both hubs for interaction and potential venues for abuse. Detecting
and mitigating cyberbullying is critical to creating a safe online environment. Machine
learning offers powerful tools to analyze large volumes of social media data and identify
patterns of abusive or harmful behavior in real time. By leveraging natural language
processing (NLP) and sentiment analysis, machine learning algorithms can detect
offensive language, threats, and harassment, enabling proactive measures to combat
cyberbullying. This presentation explores the techniques, datasets, and challenges in
implementing an effective machine learning-based solution for cyberbullying detection.
Existing System
The existing features of the project include Admin Registration and Login for secure
.
access, Post Submission for analyzing user content, and advanced Cyberbullying
Detection Algorithms (e.g., SVM, Decision Trees, Naive Bayes) supported by studies like
Zhang et al. (2018) and Dinakar et al. (2012). It integrates datasets for training and testing,
enabling Real-Time Content Analysis, as highlighted by Al-Garadi et al. (2016). Feature
Extraction techniques, such as stop word removal, enhance detection accuracy, while
Performance Metrics ensure algorithm evaluation.
Key functionalities like User Post Monitoring and Session Management allow
administrators to review flagged posts, and the Basic User Interface ensures seamless
navigation. These features align with prior research, providing a solid framework for
detecting cyberbullying effectively.
Disadvantage of Existing System

•Lack of Real-Time Intervention


•Limited User Oversight
•Dependence on Pre-Trained Models
•Inadequate User Reporting Mechanisms
•Limited Dataset Diversity
•Minimal Scalability for Large Platforms
•Absence of Advanced Moderation Tools
•Potential for False Positives and Negatives
•Lack of Customization Options for Users
•Inefficiency in Handling Multilingual Content
Proposed System
To enhance the functionality, scalability, and overall management of the
cyberbullying detection system, we propose the addition of a comprehensive User
Module. This feature will serve as the backbone of the system, empowering
administrators with advanced tools and capabilities to oversee, manage, and
optimize its operations. The Admin Module will act as a centralized control hub,
offering enhanced monitoring of user activity, real-time intervention capabilities, and
the ability to customize detection parameters to align with emerging trends in online
behavior. By integrating machine learning insights, real-time analytics, and robust
user management tools, the User Module will ensure the system operates with
higher accuracy and efficiency. Ultimately, the addition of the User Module will not
only improve the system's overall reliability but also create a safer, more inclusive
digital space for all users.
Advantage of Proposed System

•Enhanced Monitoring and Oversight


•Improved Detection Accuracy
•Streamlined User Management
•Data-Driven Decision Making
•Scalability and Flexibility
•Real-Time Intervention
•Enhanced Transparency and Accountability
•Customization for Specific Needs
•Proactive Risk Mitigation
•Improved User Experience
System Architecture
UML Diagrams

Class Diagram
Usecase Diagram
Sequence Diagram
System Analysis
This cyberbullying detection project uses machine learning and NLP to identify harmful

content on social media. Challenges like false positives, scalability, and limited control

are addressed by integrating an Admin Module, allowing real-time oversight, dataset

refinement, and intervention. The system ensures scalability, multilingual support, and

enhanced accuracy for improved platform safety and user protection.

This ensures a proactive approach to maintaining a safe and inclusive digital

environment.
Output
System Requirements

HARDWARE REQUIREMENTS:

• System : Pentium IV 2.4 GHz.


• Hard Disk : 40 GB.
• RAM : 512 Mb.

SOFTWARE REQUIREMENTS:

• Operating system : Windows


• Coding Language : Python
Conclusion
Cyber bullying across internet is dangerous and leads to mis happenings like
suicides, depression etc, and therefore there is a need to control its spread.
Therefore, cyber bullying detection is vital on social media platforms. With
availability of more data and better classified user information for various
other forms of cyber attacks Cyber bullying detection can be used on social
media websites to ban users trying to take part in such activity In this paper
we proposed an architecture for detection of cyber bullying to combat the
situation. This project not only contributes to combating online harassment
but also lays a foundation for further innovations in ensuring digital well-
being, fostering a positive and respectful social media environment..
Thank you

You might also like