Filtering Online Harassment: ML based Cyberbullying Detectionz

Abstract

Cyber bullying has emerged as a great threat to the people on the internet. The platform, which was made for good use, is being used by some to harass people. This is actually a misuse of a great invention. Also, the nature of social media is such that these things spread very quickly due to the online communications. Many times, this spreads anonymously. Manual way of detection of cyber bullying will be very inefficient and a lot of time consuming. Thus, an automated cyber bullying detection using machine learning will come to help. This paper explores the effectiveness of various machine learning algorithms in classifying the tweets into different types of cyber bullying, including age based, ethnicity based, gender based, religious based and non cyber bullying. This automated detection using machine learning will offer a great approach to mitigate these bullying and its after effects by identifying and isolating the harmful texts and messages in real time.