Comparative Studies of Detecting Abusive Language on Twitter
TL
TL;DR
This paper conducts the first comparative study of various learning models on Hate and Abusive Speech on Twitter, and shows that bidirectional GRU networks trained on word-level features, with Latent Topic Clustering modules, is the most accurate model.
Abstract
The context-dependent nature of online aggression makes annotating large collections of data extremely difficult. Previously studied datasets in abusive language detection have been insufficient in size to efficiently train deep learning models. Recently, Hate and Abusive Speech on Twitter, a dataset much greater in size and reliability, has been released. However, this dataset has not been comprehensively studied to its potential. In this paper, we conduct the first comparative study of various learning models on Hate and Abusive Speech on Twitter, and discuss the possibility of using additional features and context data for improvements. Experimental results show that bidirectional GRU networks trained on word-level features, with Latent Topic Clustering modules, is the most accurate model scoring 0.805 F1.
References30 items
1
Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior
2
Learning to Rank Question-Answer Pairs Using Hierarchical Recurrent Encoder with Latent Topic Clustering
3
Gated Self-Matching Networks for Reading Comprehension and Question Answering
4
A Large Labeled Corpus for Online Harassment Research
5