Automated Moderation Helper System Using Artificial Intelligence Based Text Classification and Recommender System Techniques

In this paper we introduce a novel approach for text message moderation assistance, where the system can Configure itself with negatively or positively labeled sample messages. The goal of the system is to assist moderators in moderating text messages, by providing them with recommendations about which messages should be reviewed manually. The recommendations should be based on user-defined rules, as well as machine-learned rules, derived from previously accepted or rejected messages. The proposed method is able to filter messages in Hungarian or English. It is also able to learn from user feedback, in order to better understand the preferences of users.