Crowdsourcing of Hate Speech for Detecting Abusive Behavior on Social Media
Jasleen Dhillon, Varn Gupta, Rishabh Govil, Bhavya Varshney, Adwitiya Sinha · 2019
Micro blogging sites nowadays provide a platform for a person to express their thoughts and opinions without risking anything. These social media platforms do not provide any religious or political restrictions for the user to restrict them from saying what they want. People use such platforms to express their opinions on current affairs, political campaigns, day to day activities, sports, and other services. One such platform is Twitter. This paper aims at targeting the tweets shared on twitter on the basis of emotion behind them-whether it falls under the category of hate speech or not. This paper identifies hate speech by employing various machine learning algorithms. The paper also derives the context in which various words are used and based on it identifies hate speech. It tries to keep the idea of freedom of speech intact and at the same time curtail hate speech which various other algorithms have failed to do. This paper focuses on applying the hate speech check on anti-national tweets. This can help in marking the users and to demote them to engage in such activities.