Detection of Hate Speech on Social Media Using Machine Learning

Abstract

The objective of our research to detect hate speech on social media. Everyday huge amounts of data generated by users of different social media. For this research, we created a data set collecting data from twitter. This data set consists of tweets of different kinds of people of different races and religions. In this work, we followed the machine learning approach and as we know NB and SVM is the most popular algorithm for sentiment analysis and classifying text, so we used Naïve Bayes and Support Vector Machine algorithm in this work. While using NB we find accuracy rate at 94.63% and in SVM the accuracy rate was 92.32%. As the action of a particular event of social media is not only bounded only in the internet it affects the real-life events all well. Again anything spread faster on social media compared to different other media. Many people post many hatred things of social media and it hurts other's feeling and then difficulties arrive and people have to face the further consequences. By detecting hate speech we can control these things and avoid this kind of situation. So our work has value to keep social media free from a few bad things and conflict between people of different believes.