The use of the Internet and social networks for communication has significantly increased in recent years. Twitter is the third most popular worldwide Online Social Network (OSN), only after Facebook and Instagram. Compared to other OSNs, Twitter presents a simpler data model and more straightforward data access API, making it a valuable tool for studying and analyzing online behavior, including abusive patterns. This survey attempts to create a machine learning-based guide for automatic hate speech classification, including a description of Twitter's technology and terminology, social graphs, sentiment analysis concepts, and hate speech identification. This study also adopted a systematic literature review on the most advanced computing techniques involved with the subject, focusing on state-of-the-art machine learning and research directions.