Deep Learning for Hate Speech Detection: A Comparative Study

Social media has experienced incredible growth over the last decade, both in its scale and importance as a form of communication. The nature of social media means that anyone can post anything they desire, putting forward any position, whether it is enlightening, repugnant or anywhere between. Depending on the forum, such posts can be visible to many millions of people. Different forums have different definitions of inappropriate content and different processes for identifying it, but the scale of the medium means that automated methods are an important part of this task. Hate-speech is an important aspect of this inappropriate content. Hate-speech is a subjective and complex term with no single definition, however. Irrespective of the definition of the term or the problem, it is clear that automated methods for detecting hate-speech are necessary in some circumstances. In such cases it is critical that the methods employed are accurate, effective, and efficient. A variety of methods have been explored for the hate speech detection task, including traditional classifiers [6, 17, 32, 41,57], deep learning-based classifiers [1,7,8,46,59], or the combination of both approaches [7,25,37].