Deep Learning For User Comment Moderation
John Pavlopoulos, Prodromos Malakasiotis, Ion Androutsopoulos . Proceedings of the First Workshop on Abusive Language Online 2017 – 104 citations
Experimenting with a new dataset of 1.6M user comments from a Greek news portal and existing datasets of English Wikipedia comments, we show that an RNN outperforms the previous state of the art in moderation. A deep, classification-specific attention mechanism improves further the overall performance of the RNN. We also compare against a CNN and a word-list baseline, considering both fully automatic and semi-automatic moderation.