Answers are grounded in this paper and cite their sources.
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.
No takes yet. Share an insight, caveat, or question.
Pavlopoulos et al. (2017) studied this question.