Abstract
Experimenting with a dataset of approximately 1.6M user comments from a Greek news sports portal, we explore how a state of the art RNN-based moderation method can be improved by adding user embeddings, user type embeddings, user biases, or user type biases. We observe improvements in all cases, with user embeddings leading to the biggest performance gains.
Cite
CITATION STYLE
Pavlopoulos, J., Bakagianni, J., Androutsopoulos, I., & Malakasiotis, P. (2017). Improved abusive comment moderation with user embeddings. In EMNLP 2017 - 2nd Workshop on Natural Language Processing Meets Journalism, NLPmJ 2017 - Proceedings of the Workshop (pp. 51–55). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/w17-4209
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
