International Research Journal of Engineering and Technology (IRJET) Volume: 12 Issue: 05 | May 2025
www.irjet.net
e-ISSN: 2395-0056 p-ISSN: 2395-0072
Cyberbullying Detection with Machine Learning Techniques Y Jyothika1, Likitha R2, Soundarya H J3 ,Dr. J Amutharaj4 Department of Information Science and Engineering 1-4 , Rajarajeswari College Of Engineering India1-4 ---------------------------------------------------------------------***--------------------------------------------------------------------Environment, Revenge, and Retaliation. Since offender is Abstract – The rise of social media platforms has hidden to the victim, the problem statement gets complex. With the multiplication of online life and internet access, the act of cyber bulling too has increased, and it’s difficult to detect. Thus, it is necessary to detect cyber bullying in order to protect adolescents. In this research, this vital data is utilized and information in the form of texts to improve the existing cyber bullying detection performance.
inadvertently facilitated the spread of cyberbullying, affecting numerous young individuals. As these platforms proliferate, so does the prevalence of online harassment. This study introduces a machine learning-based approach to detect cyberbullying on social media, particularly Twitter. By leveraging Natural Language Processing (NLP) to analyze textual data and Long Short Term Memory (LSTM) networks for image recognition, the proposed model aims to identify bullying content effectively. The system utilizes Twitter's API to retrieve tweets, which are then processed using classifiers like XGBoost and Decision Trees to determine the presence of bullying behavior. However, many social media bulling detection techniques have been implemented, but many of them were textual based. The objective of our project work is to show the implementation of NLP and LSTM which will identify and classify tweets, posts, and other content associated with bullying. Accordingly, machine learning model is proposed to detect and prevent bullying on Twitter. Two classifiers i.e. NLP(Natural Language Processing) are used for identifying the complete sentence in the comments and LSTM(Long Short Term Memory) for image identification. Both NLP and LSTM were able to detect the true positives with more accuracy. Also, Twitter API is used to fetch tweets and tweets are passed to the model to detect whether the tweets are bullying or not along with we use XGBoost and Decision Tree algorithms.
To address this, we propose a system which employs natural language processing techniques and the classification is done using machine learning approach that incorporates various classification techniques. 1.1 Purpose and Scope The purpose of this project is to provide a desktop UI applications for classification of hate speech. To identity the maximum number of hate speech related tweets from twitter as soon as it is posted by users. The problem can be framed as a multi-class classification task, where tweets are categorized into three distinct classes: hate speech (HS), nonhate speech (NHS), or offensive content. This application can be used to classify the hate speech (HS), not hate speech (NHS) or offensive on social media network. 1.2 Problem Statement In today's digital era, cyberbullying poses a significant threat, leading to emotional and psychological distress among users, especially adolescents and young adults. The challenge lies in the subtlety and anonymity of such acts, making manual detection arduous.
Key Words: Cyberbullying, NLP(Natural Language Processing), LSTM(Long Short Term Memory), Twitter API, XGBoost, Decision Tree.
1.INTRODUCTION
. To address this problem there is a critical need for an automated system that can effectively detect and mitigate instances of cyberbullying on social media platforms, chat application, and other online communication channels. The goal of this project is to develop a robust and accurate cyberbullying detection system using deep learning techniques, specifically long short-term memory(LST) and logistic regression. This system should be capable of analysing text and multi media content( such as images and videos) to identify and classify instances of cyberbullying, hate speech, or offensive content in real time.
Cyberbullying, a modern manifestation of harassment, has become increasingly common with the advent of digital communication platforms. Unlike traditional bullying, cyberbullying allows perpetrators to remain anonymous, making it more challenging to detect and address. For instance, suspects in several recent hate-related terror attacks had an extensive social media history of hate related posts, suggesting that social media contributes to their radicalization. Around 87 percent of the today’s youth have witnessed some form of cyber bullying. Cyber Bulling can take different structures like Sexual Harassment, Hostile
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 1209