Cyber Bullying Detection and Classification Using Machine Learning Algorithms
Shipra Gupta, Indu Bharti Jain, Merry Saxena, Pradeepta Kumar Sarangi, Ashok Kumar Sahoo, Alok Kumar Agrawal · 2024
Cybercrime has become a significant concern for both private and public entities. Growing popularity of social media platforms and the concept of freedom to speech encouraging the negative minded people to create nuisance on social media platforms. Creating real-time monitoring systems to tackle digital criminal activities presents a complex but highly effective strategy for the prompt identification of cyberattacks. Machine Learning (ML) provides automated solutions to meet these challenges. Various ML algorithms can be employed in cybersecurity to prevent attacks and mitigate security risks. Cyberbullying which is a form of harassment on social media platforms often invites legal complicacies. This study employs three machine learning models: Logistic Regression, Naïve Bayes, and Random Forest. The dataset utilized consists of user tweets obtained from Kaggle. The experimental findings indicate that Logistic Regression outperforms the other two models, achieving an accuracy of 97% on the training data and 91% on the test data.