Multi-modal hate speech detection using machine learning

Abstract

Hate speech is a common problem that people face in any content based applications. With continuous growth of internet users and media contents, it is very hard to track down hateful speech in audio and video. Converting video or audio into text does not detect hate speech accurately as humans sometimes use not hateful words as hate speech in a sarcastic way and also uses different voice tone or shows different action in the video than text. In the research, a combined approach to detect hate speech from contents using video, audio and speech by extracting feature images, feature values extracted from audio, text and used Machine learning, Deep learning and Natural language processing to detect hate speech