@InProceedings{serra-EtAl:2017:ALW1,
  author    = {Serr\`{a}, Joan  and  Leontiadis, Ilias  and  Spathis, Dimitris  and  Stringhini, Gianluca  and  Blackburn, Jeremy  and  Vakali, Athena},
  title     = {Class-based Prediction Errors to Detect Hate Speech with Out-of-vocabulary Words},
  booktitle = {Proceedings of the First Workshop on Abusive Language Online},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, BC, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {36--40},
  abstract  = {Common approaches  to text categorization essentially rely either on n-gram
	counts or on word embeddings. This presents important difficulties in highly
	dynamic or quickly-interacting environments, where the appearance of new words
	and/or varied misspellings is the norm. A paradigmatic example of this
	situation is abusive online behavior, with social networks and media platforms
	struggling to effectively combat uncommon or non-blacklisted hate words. To
	better deal with these issues in those fast-paced environments, we propose
	using the error signal of class-based language models as input to text
	classification algorithms. In particular, we train a next-character prediction
	model for any given class and then exploit the error of such class-based models
	to inform a neural network classifier. This way, we shift from the ‘ability
	to describe’ seen documents to the ‘ability to predict’ unseen content.
	Preliminary studies using out-of-vocabulary splits from abusive tweet data show
	promising results, outperforming competitive text categorization strategies by
	4-11%.},
  url       = {http://www.aclweb.org/anthology/W17-3005}
}