The incidence of online hate speech has experienced a significant increase in recent years, mostly ascribed to the widespread accessibility of platforms that enable individuals from various backgrounds to openly articulate their perspectives. The primary driver of this development can be attributed to the substantial expansion of mobile computing devices and the Internet. The extant academic literature suggests that the encounter with hate speech on online platforms has substantial consequences in real-life situations, especially for vulnerable communities. As a result, there has been considerable scholarly attention directed towards research efforts centred on the automated detection and identification of hate speech. However, there is a lack of scholarly study about the possible application of social networking sites in identifying geographical areas with an increased likelihood of hate crimes. Hate speech can inflict significant harm upon specific groups of individuals, with certain populations exhibiting heightened vulnerability to the adverse repercussions it entails. The process of automatically gathering and assessing texts generated online can provide challenges for linguistic minority groups whose languages lack the necessary computational resources. The task of automatically detecting hate speech on social media platforms poses a substantial obstacle. This study utilizes artificial intelligence approaches in the fields of text processing and natural language processing to present a methodology for identifying and categorizing hate speech on social networking platforms. The collection of data is initiated by employing various keywords in order to detect occurrences of hate speech on social media sites. The final phase entails the application of machine learning techniques to classify texts into discrete categories. In summary, we evaluate the suggested approaches and analyze the outcomes of the hate speech identification problem through the utilization of both test and training datasets.