Abstract: Our paper provides detection of Cyberbullying using machine learning. In this project, we aim to build a system that tackles Cyberbullying by identifying the mean-spirited comments and also categorizing the comments as bullied one or not. The goal of this project is to show the implementation of software that will detect bullied tweets. A machine learning model is proposed to detect and prevent bullying on Twitter. Social media is a platform where many people are getting bullied. To identify word similarities in the tweets made by bullies and make use of machine learning and detect social media bullying actions. As social networking sites are increasing, cyberbullying is increasing day by day in today’s world. Cyberbullying is a crime in which a perpetrator targets a person with online harassment and hate. As to detect the cyberbullying a GUI (Graphical User Interface) is created to detect where tweets are used to detect the cyberbullying. Cyberbullying includes insulting, humiliating and making fun of people on social media that can cause mental breakdowns for the victims, it can affect one physically as well to the extent that can also lead to suicidal attempts. We are using classifiers- Naive Bayes, SVM (Support Vector Machine), Random Forest, Decision Tree and Sklearn. As for the classification phase, machine learning will be used. Two classifiers i.e., SVM and Naïve Bayes are used for training and testing the Twitter bullying content. Both Naive Bayes and SVM (Support Vector Machine) were able to detect the true positives with 71.25% and 52.70% accuracy respectively. But Naive Bayes outperforms SVM of similar work on the same dataset.
Keywords: Cyberbullying detection ∙ Machine Learning ∙ Twitter∙ Tweets ∙ Online harassment.
| DOI: 10.17148/IJARCCE.2021.101272