Learning Representations for Detecting Abusive Language

摘要

This paper discusses the question whether it is possible to learn a generic representation that is useful for detecting various types of abusive language. The approach is inspired by recent advances in transfer learning and word embed-dings, and we learn representations from two different datasets containing various degrees of abusive language. We compare the learned representation with two standard approaches; one based on lexica, and one based on data-specific n-grams. Our experiments show that learned representations do contain useful information that can be used to improve detection performance when training data is limited.