Hate Speech Detection: Performance Based upon a Novel Feature Detection †
Hate speech is abusive or stereotyping speech against a group of people, based on characteristics such as race, religion, sexual orientation, and gender. Internet and social media have made it possible to spread hatred easily, fast, and anonymously. The large scale of data produced through social media platforms requires the development of effective automatic methods to detect such content. Hate speech detection in short text on social media has become an active research topic in recent years, as it differs from the traditional information retrieval for documents. My research is to develop a method to effectively detect hate speech based on deep learning techniques. I have proposed a novel feature based on the lexicon of short text. Experiments have shown that proposed deep-neural-network-based models improve the performance when a novel feature combines with CNN and SVM.
Open Access Status
This publication may be available as open access