Semantic analysis of offensive languages on social media platform using Facebook as a case study

Description

Abstract People in Online Social Network websites form social aggregations, called online communities. These online communities have become the new frontier in today’s social relationships and provide great places for self-expression and the exchange of ideas. Many of them, such as Facebook, have grown to huge communities with millions of registered members. Unfortunately, offensive language has spread into almost every corner of online communities. A study, done by ScanSafe, shows that up to 80% of blogs contain offensive language. Posting messages with offensive language intentionally have become a major way of cyber-bullying in online communities. To users, offensive language can be very harmful to their mental health, especially for children and youth. To the online community, the deluge of offensive language undermines the community’s reputation, drives users away, and even directly affects its growth.  When offensive language is detected in a user message, a problem arises about how the offensive language should be removed. To solve this problem, the filtering approach is known to produce the best filtering result.