Scribd
Upload
17 views

yshu ppt - Copy

The project focuses on detecting cyberbullying on social media using machine learning and natural language processing, achieving over 90% accuracy on Twitter and 80% on Wikipedia data. It proposes a binary classification model that identifies hate speech and personal attacks, addressing limitations of existing systems. The study emphasizes the importance of regulating social media content to mitigate the severe consequences of cyberbullying.

Uploaded by

Pavitra Vaishnavi
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
17 views

yshu ppt - Copy

The project focuses on detecting cyberbullying on social media using machine learning and natural language processing, achieving over 90% accuracy on Twitter and 80% on Wikipedia data. It proposes a binary classification model that identifies hate speech and personal attacks, addressing limitations of existing systems. The study emphasizes the importance of regulating social media content to mitigate the severe consequences of cyberbullying.

Uploaded by

Pavitra Vaishnavi
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/ 23

Department of Information Technology

Mini Project Review-I


Presentation
On
Detection of Cyberbullying on Social Media Using Machine learning

Team Mates Under the Guidance of


Pavitra Vaishnavi -21J41A1242 Mr.T.Nagarjuna Reddy
P Madhav Reddy - 21J41A1254 Assistant Professsor
Shaik Sameer - 21J41A1252
Nakka Rajeev - 21J41A1239
Abstract
Cyberbullying on the internet impacts both
teenagers and adults, often results in severe
consequences like depression and suicide.
Regulating social media content is essential.
This study analyzes hate speech tweets from
Twitter and personal attack comments from
Wikipedia to build a cyberbullying detection
model using NLP & machine learning. With
three feature extraction methods and four
classifiers, the model achieves over 90%
accuracy on Twitter data and over 80% on
Wikipedia data.
Objective
The main objective is to identify the cyberbullying text and
also take its meaning into consideration. This project is to
develop an efficient binary classification model to detect
cyberbullying in text data from social media platforms. This
model provides accuracy of over 80-90% for Twitter and
Wikipedia data.
Existing System
 This project was developed to detect and identify the fake
profiles providing the accuracy of 68%.

 Multiple detection nodes connected where each nodes uses


either different or same algorithm for the data and resultant
were combined to produce results.

 Here,
• B-LSTM technique
• KNN model are used to get accurate precision.
Disadvantages
 A vocabulary is not designed
from all the documents.

 Tf-Idf is a popular technique,


it may not be optimal for all
text classification tasks,
particularly when dealing with
short, noisy text like social
media posts.
Proposed System
Cyberbullying detection is solved in this project as a
binary classification problem where we are detecting two
majors form of Cyberbullying: hate speech on Twitter and
Personal attacks on Wikipedia and classifying them as
containing Cyberbullying or not.

 Tokenization

 Stemming

 Stop word Removal


Algorithms
 Support Vector Machine
 Logistic Regression
 Naive Bayes

Advantages
 Common Bag-of-Words Model handles single-word and multi-word inputs. Predicts word based on
context.
 CBOW Model Captures multiple semantic meanings of a word.
SYSTEM REQUIREMENTS :- SOFTWARE REQUIREMENTS :-

  Operating system : Windows 7 Ultimate.


H/W System Configuration:-
  Coding Language: Python.
Processor - Pentium –IV
  Front-End : Python.
RAM - 4 GB (min)
  Back-End : Django-ORM
Hard Disk - 20 GB
 Designing : Html, css, javascript.
 Data Base : MySQL (WAMP Server).
Design and Implementation
Use Case Diagram
Class Diagram
Sequence Diagram
Data Flow Diagram
Flow Chart- Remote User
Flow Chart- Service Provider
#!/usr/bin/env python
Code """Django's command-line utility for administrative tasks."""
import os
import sys

def main():
"""Run administrative tasks."""
os.environ.setdefault('DJANGO_SETTINGS_MODULE',
'detection_of_cyberbullying.settings')
try:
from django.core.management import execute_from_command_line
except ImportError as exc:
raise ImportError(
"Couldn't import Django. Are you sure it's installed and "
"available on your PYTHONPATH environment variable? Did you "
"forget to activate a virtual environment?"
) from exc
execute_from_command_line(sys.argv)
if __name__ == '__main__':
main()
Result
Conclusion
The cyberbullying detection model
effectively identifies hate speech and
personal attacks with high accuracy on
Twitter and Wikipedia data. This
approach highlights the potential of NLP
and machine learning in creating safer
online environments.
REFERENCES
[1] P. Galán-García, J. G. de la Puerta, C. L. Gómez, I. Santos, and P. G. Bringas, “Supervised
machine learning for the detection of troll profiles in twitter social network: Application to a
real case of cyberbullying,” 2014, doi: 10.1007/978-3-319-01854-6_43.
[2] A. Mangaonkar, A. Hayrapetian, and R. Raje, “Collaborative detection of cyberbullying
behavior in Twitter data,” 2015, doi:10.1109/EIT.2015.7293405.
[3] R. Zhao, A. Zhou, and K. Mao, “Automatic detection of cyberbullying on social networks
based on bullying features,” 2016, doi: 10.1145/2833312.2849567.
[4] M. Dadvar and K. Eckert, “Cyberbullying Detection in Social Networks Using Deep
Learning Based Models; A Reproducibility Study,” arXiv. 2018.
Thank You
PROB

You might also like