Framework for Detection of Cyberbullying in Text Data Using Natural Language Processing and Machine Learning
C. V. Suresh Babu, S. Kowsika, Madduri Tejaswi, T. R. Janarakshani, S. Mercysha Princy · Advances in digital crime, forensics, and cyber terrorism book series · 2023
Cyberbullying is a huge problem online that affects young people and adults. It can lead to accidents like suicide and depression. There is a growing need to curate content on social media platforms. In the following study, the authors used data on two different forms of cyberbullying, hate speech tweets on Twitter, and ad hominem-based comments on Wikipedia forums. The authors use machine learning-based natural language processing and textual data to build models based on cyberbullying detection. They study three feature extraction methods and their four classifiers to determine the best method. The model achieves an accuracy of more than 90 degrees on the tweet data and more than 80 degrees on the Wikipedia data.