Hate Speech Detection in Social Media Surveillance: A Review of Related Literature

Abstract

Social media surveillance is a requirement for governments and intelligence agencies around the world to detect and prevent hate crimes. The dynamic and unstructured nature of the textual content available on social media platforms makes it very complex to extract hate related speech patterns from this content. It also creates ambiguities in the data and therefore, data mining techniques become difficult to apply in this scenario. Several alternative techniques were adopted by different researchers in the past to cope with this problem and to capture and analyze such unstructured text for the purpose of hate speech detection. In this paper, we reviewed, categorized and presented a state-of-the-art of these techniques which were divided in to three categories namely text mining, sentiment analysis and semantics. The challenges in the application of the existing techniques were also discussed and these can be taken up as future directions