Scribd
Upload
17 views

Abs 1

The document outlines the development of an application utilizing deep learning techniques to detect cyberbullying on social media platforms. It proposes a CNN-BiLSTM model that enhances detection accuracy by analyzing text patterns and contextual dependencies, addressing the limitations of existing machine learning methods. The system aims for real-time monitoring and intervention to improve online safety and mental health support.

Uploaded by

mailtochipmatrix
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
17 views

Abs 1

The document outlines the development of an application utilizing deep learning techniques to detect cyberbullying on social media platforms. It proposes a CNN-BiLSTM model that enhances detection accuracy by analyzing text patterns and contextual dependencies, addressing the limitations of existing machine learning methods. The system aims for real-time monitoring and intervention to improve online safety and mental health support.

Uploaded by

mailtochipmatrix
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

An application to Detect Cyberbullying Using Machine Learning and Deep

Learning Techniques
OBJECTIVE:
Need to implement an application using Deep learning algorithms to Detect Cyberbullying
ABSTRACT:
With the extensive use of social media comes many downsides and one of the downsides is
cyberbully. Cyberbullying is a form of online harassment that is both unsettling and
troubling. It can take many forms, but the most common is a textual format. Cyberbullying is
common on social media, and people often end up in a mental breakdown state instead of
taking action against the bully. On the majority of social networks, automated detection of
these situations necessitates the use of intelligent systems. We have proposed a cyberbullying
detection system to address this issue. In this work, we proposed a deep learning framework
that will evaluate real-time twitter tweets or social media posts as well as correctly identify
any cyberbullying content in them. Recent studies has shown that deep neural network-based
approaches are more effective than conventional techniques at detecting cyberbullying texts.
SYSTEM DESCRIPTION:
Detecting cyberbullying using machine learning and deep learning techniques involves
analyzing text, images, and interactions on digital platforms to identify harmful behavior.
Machine learning algorithms can classify and flag abusive language by learning from labeled
datasets of cyberbullying incidents. Deep learning models, particularly those based on natural
language processing (NLP), enhance detection accuracy by understanding context and
sentiment in communications. Combining these approaches allows for real-time monitoring
and intervention, improving online safety and mental health support. Continuous model
training and updates are essential to adapt to evolving cyberbullying tactics and language
trends.
EXISTING METHOD:
Machine learning-based cyberbully detection leverages algorithms to identify and flag
harmful online behavior. By training on extensive datasets of text and interactions, these
models can recognize abusive language and patterns with high accuracy. They preprocess
data to extract relevant features, apply learning algorithms to classify content, and
continuously improve through ongoing updates. This technology enables real-time
monitoring and intervention, helping to create safer digital spaces by promptly addressing
instances of cyberbullying.
DISADVANTAGES OF EXISTING METHOD:
 ML gives less performance
 Unable to handle huge datasets
 It takes more time to detect and classify it
PROPOSED METHOD:
The CNN-BiLSTM model for cyberbully detection combines Convolutional Neural
Networks (CNNs) and Bidirectional Long Short-Term Memory (BiLSTM) networks to
enhance text analysis. CNNs extract local features from textual data by scanning for patterns,
while BiLSTMs capture contextual dependencies by processing text in both forward and
backward directions. This hybrid approach improves the model's ability to understand and
classify nuanced cyberbullying content, making it highly effective for detecting abusive
language and behavior in real time.

ADVANTAGES:
 Drastically reduce the time required for detection and classification
 Accuracy rate is greater than existing method
 Better performance
.
SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

 System : Pentium IV 2.4 GHz.


 Hard Disk : 40 GB.
 Floppy Drive : 44 Mb.
 Monitor : 15 VGA Colour.
 Mouse :
 Ram : 512 Mb.

SOFTWARE REQUIREMENTS:

 Operating system : Windows 10/7.


 Language :Python
 IDE :Anaconda, Notebook

You might also like