Novel Hate Speech Detection Using Word Cloud Visualization and Ensemble Learning Coupled with Count Vectorizer

A plethora of negative behavioural activities have recently been found in social media. Incidents such as trolling and hate speech on media, especially Twitter, grown considerably. Therefore, detection Twitter has become an area interest among many researchers. In this paper, we present a computational framework to (1) examine out the challenges behind (2) generate high performance results. First, extract features from data by utilizing count vectorizer technique. Then, provide labeled dataset constructed adopted ensemble methods, including Bagging, AdaBoost, Random Forest. After training, classify new tweet examples into one two categories, or non-hate speech. Experimental results show that Forest surpassed other methods generating 95% using accuracy word cloud displays most prominent tweets are responsible for hateful sentiments.