Cybercrime has emerged as a result of rising Internet usage and easier access to online groups like social media. Today, cyberbullying is a pretty regular occurrence. In recent days, it appears that riots were caused by some statements made by one community against another. This study explores the application of machine learning techniques for detecting cyberbullying across various online platforms. Traditional methods of monitoring online behavior are often inadequate due to the scale and rapid evolution of abusive language. Our approach leverages machine learning algorithms to automatically classify and detect bullying content, using text analysis on social media comments and messages. We employ Natural Language Processing (NLP) techniques, such as tokenization, lemmatization, and sentiment analysis, to process textual data and capture underlying sentiments. Algorithms like Support Vector Machines (SVM), Naïve Bayes, and neural networks are trained on labeled datasets of cyberbullying content to distinguish harmful messages from benign ones. The proposed system demonstrates promising results in identifying potential cyberbullying instances, aiming to create safer online environments. By providing real-time detection capabilities, this research contributes to preventive measures that could reduce online harassment, raising awareness and fostering healthier digital interactions.
Read full abstract