Deep Learning for User Comment Moderation

John Pavlopoulos, Prodromos Malakasiotis, Ion Androutsopoulos


Abstract
Experimenting with a new dataset of 1.6M user comments from a Greek news portal and existing datasets of EnglishWikipedia 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.
Anthology ID:
W17-3004
Volume:
Proceedings of the First Workshop on Abusive Language Online
Month:
August
Year:
2017
Address:
Vancouver, BC, Canada
Venues:
ALW | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
25–35
Language:
URL:
https://www.aclweb.org/anthology/W17-3004
DOI:
10.18653/v1/W17-3004
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W17-3004.pdf