"Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection
William Yang Wang
- Vol. 2, pp 422-426
Reads0
Chats0
TLDR
Li et al. as discussed by the authors designed a hybrid convolutional neural network to integrate meta-data with text and showed that this hybrid approach can improve a text-only deep learning model.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.read more
Citations
More filters
Journal ArticleDOI
Early Detection of Social Media Hoaxes at Scale
Arkaitz Zubiaga,Aiqi Jiang +1 more
TL;DR: This work introduces a semi-automated method that leverages the Wikidata knowledge base to build large-scale datasets for veracity classification, focusing on celebrity death reports, to create a dataset with 4,007 reports including over 13M tweets, 15% of which are fake.
Proceedings ArticleDOI
A Multi-Level Attention Model for Evidence-Based Fact Checking
TL;DR: The authors proposed a model that enables inter-sentence attentions at different levels and can benefit from joint training, which outperforms the graph-based approaches and yields 1.09% and 1.42% improvements in label accuracy and FEVER score.
Book ChapterDOI
Misinformation in the Chinese Weibo
Lu Xiao,Sijing Chen +1 more
TL;DR: The potentially severe negative impact these posts can impose on the society as they undermine Weibo users’ trustfulness to others and to the social media platform is discussed.
Proceedings ArticleDOI
Latent Retrieval for Large-Scale Fact-Checking and Question Answering with NLI training
TL;DR: It is shown that training a dense retriever is sufficient to outperform traditional sparse representations in both question answering and fact-checking and that pre-training with Factual-NLI, and other NLI datasets, is also effective for large-scale passage retrieval in question answering.
Journal ArticleDOI
A Survey on Explainable Fake News Detection
TL;DR: An overview of explainable fake news detection models can be found in this paper , where the authors present an overview of existing models, datasets, evaluation techniques, and visualization processes, and possible improvements in this field are identified and discussed.
References
More filters
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Posted Content
Efficient Estimation of Word Representations in Vector Space
TL;DR: This paper proposed two novel model architectures for computing continuous vector representations of words from very large data sets, and the quality of these representations is measured in a word similarity task and the results are compared to the previously best performing techniques based on different types of neural networks.
Proceedings ArticleDOI
Convolutional Neural Networks for Sentence Classification
TL;DR: The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification, and are proposed to allow for the use of both task-specific and static vectors.
Journal Article
Natural Language Processing (Almost) from Scratch
TL;DR: A unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including part-of-speech tagging, chunking, named entity recognition, and semantic role labeling is proposed.
Proceedings Article
Character-level convolutional networks for text classification
TL;DR: In this paper, the use of character-level convolutional networks (ConvNets) for text classification has been explored and compared with traditional models such as bag of words, n-grams and their TFIDF variants.