ABSTRACT

Social media is quickly evolving in front of our eyes and it is almost impossible to reject and hide from this new form of media. Not exclusively is it an imperative piece of socialization inside companion gatherings however at this point it is utilized to advertise and propel individuals to turn into a piece of a bigger network.. But, young creators in this community are suffering from child predatory comments from users which consists of un-parliamentary words that affect the society a lot. One such platform, called YouTube has recently faced a lot of trouble due to the unavoidable predatorily comments. The platform has disabled many comment sections associated with this problem. The existing system allows discarding of post manually, only if an user reports issue, or disabling the entire comment section, thereby restraining both subscribers and creators interaction with each other. This project focuses on filtering and disabling only those comments that contains profanity and vulgar words ,even before its post using Full text search algorithm. The comment is cleaved word by word and is scrutinized with a trained dataset using Elasticsearch cloud based application. If found any word, an message is displayed to the user, else the comment as typed is displayed in the section.