Abusive Content Detection in Online User-Generated Data: A survey.

The proliferation of social media platforms resulted in a remarkable increase in user-generated content. These platforms have empowered users to create, share and exchange content for interacting and communicating with each other. However, these have also opened new avenues to cyber-bullies and haters who can spread their negativity to a larger audience, often anonymously. Due to the pervasiveness and severity of this behavior, many automated approaches that employ natural language processing (NLP), machine learning and deep learning techniques have been proposed in the past. This survey offers an extensive overview of the state-of-the-art approaches proposed by research community to identify offensive content. Based on our comprehensive literature survey, a categorization of different approaches and features employed by the researchers in the detection process are presented. This survey also incorporates the major challenges that require considerable research efforts in this domain. Finally, future research directions with an aim of developing robust abusive content detection system for social media are also discussed. [ABSTRACT FROM AUTHOR]