As a result of the ease with which any viewpoint may be posted on social networking sites, online hate speech has become more widespread in recent years. This trend is mostly attributable to the fast growth of mobile computers and the Internet. Studies that were done in the past demonstrate that being exposed to hate speech online has substantial implications in real life for historically disadvantaged populations. As a result, there has been a lot of interest in research on the automatic identification of hate speech. Nevertheless, there has not been a lot of research done on how social networking sites might help identify communities that are prone to hate crimes. It is possible for hate speech to have an effect on any demographic group; however, certain groups are more susceptible to the effects of hate speech than others. For example, it is difficult for racial or ethnic groups whose languages have limited computing resources to automatically gather and evaluate online generated texts. This is to say nothing of the difficulty of automatically detecting hate speech on social networking sites. In this article, we present a method for the identification of hate speech posted on social networking sites, applying artificial intelligence methods in text processing and natural language processing. In order to detect, hate speech on social media, firstly, we collect data by using different keywords. Secondly, we apply machine learning algorithms to classify texts into several categories. Thirdly, we evaluate the proposed approaches and assess the result of hate speech detection problem in training and test sets.