Improved Abusive Comment Moderation with User Embeddings
This work addresses abusive content moderation for online platforms, but it is incremental as it builds on existing methods with minor modifications.
The paper tackled abusive comment moderation by enhancing an RNN-based method with user embeddings and biases on a dataset of 1.6M Greek news sports comments, resulting in performance improvements, with user embeddings yielding the biggest gains.
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.