Deep-learning-based models have been successfully applied to the problem of detecting fake news on social media. While the correlations among news articles have been shown to be effective cues for online news analysis, existing deep-learning-based methods often ignore this information and only consider each news article individually. To overcome this limitation, we develop a graph-theoretic method that inherits the power of deep learning while at the same time utilizing the correlations among the articles. We formulate fake news detection as an inference problem in a Markov random field (MRF) which can be solved by the iterative mean-field algorithm. We then unfold the mean-field algorithm into hidden layers that are composed of common neural network operations. By integrating these hidden layers on top of a deep network, which produces the MRF potentials, we obtain our deep MRF model for fake news detection. Experimental results on well-known datasets show that the proposed model improves upon various state-of-the-art models.
Nguyen, MD, Do Huu, T, Calderbank, R & Deligiannis, N 2019, Fake news detection using deep Markov random fields. in Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL). NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, vol. 1, pp. 1391–1400, Annual Conference of the North American Chapter of the Association for Computational Linguistics, Minneapolis, Minnesota, United States, 2/06/19. https://doi.org/10.18653/v1/N19-1141
Nguyen, M. D., Do Huu, T., Calderbank, R., & Deligiannis, N. (2019). Fake news detection using deep Markov random fields. In Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) (pp. 1391–1400). (NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference; Vol. 1). https://doi.org/10.18653/v1/N19-1141
@inproceedings{745bd784dc50411f8ad93312e7906ce5,
title = "Fake news detection using deep Markov random fields",
abstract = "Deep-learning-based models have been successfully applied to the problem of detecting fake news on social media. While the correlations among news articles have been shown to be effective cues for online news analysis, existing deep-learning-based methods often ignore this information and only consider each news article individually. To overcome this limitation, we develop a graph-theoretic method that inherits the power of deep learning while at the same time utilizing the correlations among the articles. We formulate fake news detection as an inference problem in a Markov random field (MRF) which can be solved by the iterative mean-field algorithm. We then unfold the mean-field algorithm into hidden layers that are composed of common neural network operations. By integrating these hidden layers on top of a deep network, which produces the MRF potentials, we obtain our deep MRF model for fake news detection. Experimental results on well-known datasets show that the proposed model improves upon various state-of-the-art models.",
keywords = "Fake news, deep learning, social media",
author = "Nguyen, {Minh Duc} and {Do Huu}, Tien and Robert Calderbank and Nikolaos Deligiannis",
year = "2019",
month = jan,
day = "1",
doi = "10.18653/v1/N19-1141",
language = "English",
series = "NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference",
pages = "1391–1400",
booktitle = "Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)",
note = "Annual Conference of the North American Chapter of the Association for Computational Linguistics, NAACL-HLT ; Conference date: 02-06-2019 Through 07-06-2019",
url = "https://naacl2019.org/",
}