A systematic literature review of different machine learning methods on hate speech detection

Abstract

Hate speech is one of the most challenging problem internets is facing today. The most common practice to deal with online suspects of hate speech is by manually reporting the comment or the post which at the back end is reviewed by a person. This has a lot of limitations. it requires a lot of time as human intervention is required. Many countries have made laws so that companies have to deal with this type of content within a time frame. This systematic literature review examines hate speech detection problem and will be used to do an experimental approach on detecting hate speech and abusive language. This work also provides an overview of previous research, including methods, algorithms, and main features used. We observe 31,633 papers of current research about hate speech detection from online databases, after applying inclusion and exclusion criteria the result is 1,929 papers and then returned 15 papers after the full text analysis. These papers are for answering the research questions of this systematic literature review. We use two research questions in this literature review which will be the foundation of the next experimental research. Correctly classifying a piece of text as an actual hate speech requires a lot of correctly labelled data. Most common challenges are different languages, out of vocabulary words, long range dependencies and many more.