ABSTRACT

Harassment on the internet is a significant issue that affects both adults and teenagers. Errors like depression and suicide have resulted from it. Social media platforms are being urged more and more to monitor their content. The research that follows builds a model for the detection of cyberbullying in text data using natural language processing and machine learning. It uses information from two different types of cyberbullying: hate speech tweets from Twitter and comments based on personal attacks from Wikipedia forums. Four classifiers and three feature extraction techniques are examined to discover which strategy is most effective. For data from Twitter, the algorithm offers accuracy levels above 90%, and for data from Wikipedia, accuracy levels above 80%. Keywords: ML, NLP, Feature extraction, SVM, RFC, Precision
Publication date: 01/11/2024

https://ijbpas.com/pdf/2024/November/MS_IJBPAS_2024_8428.pdf

Download PDF
https://doi.org/10.31032/IJBPAS/2024/13.11.8428