Classification of Harmful and Normal client data in social networks with the Help of Machine Learning
Date Issued
May 2023
Author(s)
Advisor
Abstract
Social networks have become an indispensable part of our daily lives,
allowing us to connect with friends and family, share experiences and
ideas, and stay informed about current events. However, the use of social
networks also carries potential risks, particularly with the spread of harmful
content such as hate speech, cyberbullying, and fake news. This has
led to an increasing need for social network administrators to develop efficient
methods for identifying and removing harmful content. Traditional
methods for identifying and removing harmful content are often based on
manual review and reporting by users, which can be time-consuming and
unreliable. As social networks continue to grow in size and complexity,
this approach is becoming increasingly challenging, and administrators
are turning to machine learning techniques as a more effective solution.
Machine learning algorithms can be trained to automatically analyze large
amounts of data generated in social networks and identify patterns that
distinguish harmful content from normal content. These algorithms can
also adapt and evolve over time as new types of harmful content emerge,
providing a more dynamic and responsive solution to the problem. This
study aims to explore the application of machine learning techniques to
classify harmful and normal client data in social networks. The focus will
be on developing and evaluating models that can accurately distinguish
harmful data from normal data. This will involve the use of various machine
learning techniques, such as supervised and unsupervised learning,
and feature engineering to extract relevant information from the data.
Using unsupervised algorithms aimed at detecting Harmful and Normal
clients on social networks, the outcomes of this study have the potential
to contribute to the development of more effective solutions for identifying
and removing harmful content in social networks. This could ultimately
lead to a safer and more secure online environment for users and help to
mitigate the negative effects of harmful content on individuals and society
as a whole.
allowing us to connect with friends and family, share experiences and
ideas, and stay informed about current events. However, the use of social
networks also carries potential risks, particularly with the spread of harmful
content such as hate speech, cyberbullying, and fake news. This has
led to an increasing need for social network administrators to develop efficient
methods for identifying and removing harmful content. Traditional
methods for identifying and removing harmful content are often based on
manual review and reporting by users, which can be time-consuming and
unreliable. As social networks continue to grow in size and complexity,
this approach is becoming increasingly challenging, and administrators
are turning to machine learning techniques as a more effective solution.
Machine learning algorithms can be trained to automatically analyze large
amounts of data generated in social networks and identify patterns that
distinguish harmful content from normal content. These algorithms can
also adapt and evolve over time as new types of harmful content emerge,
providing a more dynamic and responsive solution to the problem. This
study aims to explore the application of machine learning techniques to
classify harmful and normal client data in social networks. The focus will
be on developing and evaluating models that can accurately distinguish
harmful data from normal data. This will involve the use of various machine
learning techniques, such as supervised and unsupervised learning,
and feature engineering to extract relevant information from the data.
Using unsupervised algorithms aimed at detecting Harmful and Normal
clients on social networks, the outcomes of this study have the potential
to contribute to the development of more effective solutions for identifying
and removing harmful content in social networks. This could ultimately
lead to a safer and more secure online environment for users and help to
mitigate the negative effects of harmful content on individuals and society
as a whole.
Subjects
File(s)![Thumbnail Image]()
Name
Abstract-BSc-KostasMarkou_Thesis-2023.pdf
Size
163.25 KB
Format
Adobe PDF
Checksum (MD5)
3130425dc21323714bebafec1a3c6e69