Alam, Md Golam RabiulShill, Ponkoj ChandraBoishakhi, Fariha Tahosin2021-12-152021-12-1520212021-01ID 16201011ID 16201010http://hdl.handle.net/10361/15735Cataloged from PDF version of thesis.Includes bibliographical references (pages 43-45).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.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 speech45 pagesenBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Audio hate SpeechVideo hate SpeechHate Speech detectionMachine LearningMulti-modal Hate Speech detectionMachine LearningThesis