There are large number of online discussion forums on the internet which are meant for users to express exchange their views and opinions on various topics. In such forums it has been often observed that user communications sometimes quickly become inappropriate such as hurling abuses, passing rude comments on individual or communities. In appropriate messages and comments are turning into an online menace slowly degrading the effectiveness of user experiences and discussion. Hence automatic detection and filtering of such inappropriate language has become an important problem for improving the quality of conversation with users as well as virtual agent. Detecting appropriate language is challenging due to various natural language phenomenon such as spelling mistake and variations. To address concerns on children’s access to offensive content over Internet, administrators often manually review online contents to detect and delete offensive materials. However, the manual review tasks of identifying offensive contents are labor intensive, time consuming, and thus not sustainable and scalable in reality. This application identify the abusive words and simply replace it over less time. So it is scalable in reality.
sargarakshay / abusive-comments-filter Goto Github PK
View Code? Open in Web Editor NEWThere are large number of online discussion forums on the internet which are meant for users to express exchange their views and opinions on various topics. In such forums it has been often observed that user communications sometimes quickly become inappropriate such as hurling abuses, passing rude comments on individual or communities. In appropriate messages and comments are turning into an online menace slowly degrading the effectiveness of user experiences and discussion. Hence automatic detection and filtering of such inappropriate language has become an important problem for improving the quality of conversation with users as well as virtual agent. Detecting appropriate language is challenging due to various natural language phenomenon such as spelling mistake and variations. To address concerns on children’s access to offensive content over Internet, administrators often manually review online contents to detect and delete offensive materials. However, the manual review tasks of identifying offensive contents are labor intensive, time consuming, and thus not sustainable and scalable in reality. This application identify the abusive words and simply replace it over less time. So it is scalable in reality.
License: Apache License 2.0