A Review on the Detection of Offensive Content in Social Media Platforms

Offensive content refers to messages which are socially unacceptable including vulgar or derogatory messages. As the use of social media increases worldwide, social media administrators are faced with the challenges of tackling the inclusion of offensive content, to ensure clean and non-abusive or offensive conversations on the platforms they provide.  This work organizes and describes techniques used for the automated detection of offensive languages in social media content in recent times, providing a structured overview of previous approaches, including algorithms, methods and main features used.   Selection was from peer-reviewed articles on Google scholar. Search terms include: Profane words, natural language processing, multilingual context, hybrid methods for detecting profane words and deep learning approach for detecting profane words. Exclusions were made based on some criteria. Initial search returned 203 of which only 40 studies met the inclusion criteria; 6 were on natural language processing, 6 studies were on Deep learning approaches, 5 reports analysed hybrid approaches, multi-level classification/multi-lingual classification appear in 13 reports while 10 reports were on other related methods. The limitations of previous efforts to tackle the challenges with regards to the detection of offensive contents are highlighted to aid future research in this area.  Keywords — algorithm, offensive content, profane words, social media, texts