Multi-modal Hate Speech Detection using Machine Learning
This addresses the challenge of accurately identifying hate speech in multimedia for internet platforms, but it appears incremental as it builds on existing methods by combining modalities.
The researchers tackled the problem of detecting hate speech in video content by proposing a multimodal system that extracts features from images, audio, and text, using machine learning and natural language processing to improve accuracy over single-modality approaches.
With the continuous growth of internet users and media content, 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 human sometimes uses hateful words as humorous or pleasant in sense and also uses different voice tones or show different action in the video. The state-ofthe-art hate speech detection models were mostly developed on a single modality. In this research, a combined approach of multimodal system has been proposed to detect hate speech from video contents by extracting feature images, feature values extracted from the audio, text and used machine learning and Natural language processing.