Abstract:

Internet in general and social media in particular have greatly facilitated the communication, interaction and collaboration among people and different entities. As generally there is no censorship, these media sometimes are used to proliferate discourses that contain hateful messages targeting ethnic origin, religious or sexual groups, which potentially may degenerate to violent acts against individuals of such groups. Therefore, we explore the idea of building of automatic classifier that can be used for detection of hate speech in public Albanian language pages. A hate speech corpus for Albanian language is created, and then based on Support Vector Machine (SVM) approach,  an automatic hate speech detection system is proposed. Such system can be used to detect and analyze hate speech in online contents over time and to enhance our knowledge on how they affect opinion creation in society.  

Keywords: