@InProceedings{wang:2017:Short,
  author    = {Wang, William Yang},
  title     = {"Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {422--426},
  abstract  = {Automatic fake news detection is a challenging problem in deception detection,
	and it has tremendous real-world political and social impacts. However,
	statistical approaches to combating fake news has been dramatically limited by
	the lack of labeled benchmark datasets. In this paper, we present LIAR: a new,
	publicly available dataset for fake news detection. We collected a decade-long,
	12.8K manually labeled short statements in various contexts from
	PolitiFact.com, which provides detailed analysis report and links to source
	documents for each case. This dataset can be used for fact-checking research as
	well. Notably, this new dataset is an order of magnitude larger than previously
	largest public fake news datasets of similar type. Empirically, we investigate
	automatic fake news detection based on surface-level linguistic patterns. We
	have designed a novel, hybrid convolutional neural network to integrate
	meta-data with text. We show that this hybrid approach can improve a text-only
	deep learning model.},
  url       = {http://aclweb.org/anthology/P17-2067}
}