Cyberbullying detection on social media with a browser extension, using machine learning techniques
Loading...
Date
2023-10-09
Authors
Δασκαλάκης, Στυλιανός
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In today’s digital age, social media platforms have become an integral part of our
daily lives. They have clearly reformed the way we communicate, share information,
and in general the way we connect with others around the world. Among the many
of social media platforms, Twitter stands out as a prominent microblogging platform
that enables users to express their thoughts, opinions, and experiences in concise
messages called tweets.
Twitter, founded in 2006, quickly gained popularity due to its simplicity and
real-time nature. With over millions of active users, it has emerged as a powerful
tool for disseminating news, engaging in conversations, and fostering communities
around various topics. However, the rapid growth and wide usage of Twitter have
also led to certain challenges, one of the most significant being cyberbullying.
Cyberbullying, defined as the use of digital technologies to harass, intimidate,
or harm individuals online, has become a pressing issue in today’s interconnected
world. Social media platforms, including Twitter, have provided a virtual space
where cyberbullying incidents can occur, often leading to severe emotional and
psychological consequences for the victims. Recognizing the harmful impact of
cyberbullying, researchers and practitioners have been actively exploring ways to
detect and mitigate such behavior on social media platforms.
In recent years, breakthroughs in the field of Machine Learning have unlocked
new possibilities for addressing complex problems like cyberbullying detection.
Machine Learning, a subfield of Artificial Intelligence (AI), involves training artificial
neural networks to learn and extract meaningful patterns from vast amounts of data.
By leveraging its power, it becomes feasible to build intelligent systems that can
automatically identify and flag instances of cyberbullying on social media platforms
like Twitter.
The objective of this thesis is to develop and implement a Chrome extension that
utilizes Machine Learning techniques to detect cyberbullying on Social Media. It
will be applied and examined in the Twitter platform: The extension will analyze the
content of tweets and provide users with appropriate warnings or interventions. By
integrating this tool into the Twitter browsing experience, users can enhance their
safety and well-being while engaging in online interactions.
The subsequent sections of this thesis will delve into the details of the proposed
implementation, including the selection, training, and comparison of Machine
Learning models, the development of the Chrome extension, and the evaluation
of its performance in detecting cyberbullying incidents on Twitter.
By creating an effective and user-friendly solution, we aim to contribute to
the ongoing efforts in combating cyberbullying and promoting a healthier online
environment on social media platforms like Twitter.
Description
Keywords
Social media platforms, Twitter