Abstract
Often dismissed as a harmless pastime for the gullible, pseudoscience nonetheless has devastating effects, including the loss of life. Its menace is amplified by the difficulty of differentiating pseudoscience from science, especially for the untrained eye. A novel method recognizes pseudoscience in the text by utilizing a fine-tuned Robustly Optimized Bidirectional Encoder Representation from Transformers Approach (RoBERTa) model. The dataset of 112,720 full-text articles used in this work is made publicly available to remedy the lack of datasets related to pseudoscience. A novel technique, Intelligent ReLabeling (IRL), is employed to minimize mislabeled data, enabling the rapid creation of high-quality textual datasets. IRL eliminates the need for expensive manual verification processes and minimizes domain expertise requirements in many applications. The final model trained with IRL achieves an F1 score of 0.929 on a separate manually labeled test dataset.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
See Sect. 3.1 for details.
- 2.
The manual verification was performed by the authors through fact-checking against reliable sources as appropriate.
- 3.
We will make the code for IRL publicly available, along with experimentally demonstrating its effectiveness using the IMDB reviews dataset [25]. We artificially add noise to the labels of the IMDB reviews dataset, substantially degrading the performance of models trained on the noisy data. Then, we show that applying IRL improves the performance of the models close to or to the same levels before adding noise.
- 4.
See Sect. 3.3.
- 5.
12-layer, 768-hidden, 12-heads, 125 M parameters.
- 6.
- 7.
3 tokens reserved for special tokens.
- 8.
References
Boudry, M., Blancke, S., Pigliucci, M.: What makes weird beliefs thrive? the Epidemiology of Pseudoscience. Philos. Psychol. 28(8), 1177–1198 (2015)
Hansson, S.O.: Science and pseudo-science (2017)
Hansson, S.O.: Science denial as a form of pseudoscience. Stud. Hist. Philos. Sci. Part a 63, 05 (2017)
Pigliucci, M., Boudry, M.: The dangers of pseudoscience. New York Times 21, 1735–1741 (2013)
Douglas, K.M., Sutton, R.M.: Climate change: why the conspiracy theories are dangerous. Bull. Atom. Sci. 71(2), 98–106 (2015)
Torabi Asr, F., Taboada, M.: Big data and quality data for fake news and misinformation detection. Big Data Soc. 6(1), 2053951719843310 (2019)
Lilienfeld, S.O., Ammirati, R., David, M.: Distinguishing science from pseudoscience in school psychology: science and scientific thinking as safeguards against human error. J. Sch. Psychol. 50 (2012)
Bond, C.F., Jr., DePaulo, B.M.: Accuracy of deception judgments. Pers. Soc. Psychol. Rev. 10(3), 214–234 (2006)
Shu, K., Sliva, A., Wang, S., Tang, J., Liu, H.: Fake news detection on social media: a data mining perspective. ACM SIGKDD Explor. Newslett. 19(1), 22–36 (2017)
Niall J Conroy, Victoria L Rubin, and Yimin Chen. Automatic deception detection: Methods for finding fake news. Proc. Assoc. Inf. Sci. Technol. 52(1), 1–4, (2015)
Shvets, A.: A method of automatic detection of pseudoscientific publications. In Intelligent Systems’ 2014, pp. 533–539. Springer (2015)
Figueira, Á., Oliveira, L.: The current state of fake news: challenges´ and opportunities. Procedia Comput. Sci. 121, 817–825 (2017)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 5998–6008 (2017)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pretraining of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: Glue: a multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)
Lai, G., Xie, Q., Liu, H., Yang, Y., Hovy, E.: Race: large-scale reading comprehension dataset from examinations. arXiv preprint arXiv:1704.04683 (2017)
Rajpurkar, P., Jia, R., Liang, P.: Know what you don’t know: unanswerable questions for squad. arXiv preprint arXiv:1806.03822 (2018)
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)
Wu, Y., Schuster, M., Chen, Z., Le, Q.V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al.: Google’s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)
Pew Research Centre.: State of the news media 2016 (2004)
Zimdars, M.: False, misleading, clickbait-y, and satirical “news” sources. https://docs.google.com/document/d/10eA5-mCZLSS4MQY5QGb5ewC3VAL6pLkT53V_81ZyitM/preview, 2016
Aker, A., Vincentius, K., Bontcheva, K.: Credibility and transparency of news sources: Data collection and feature analysis (2019)
Maas, A., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 142–150, Portland, Oregon, USA, June 2011. Association for Computational Linguistics
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Rajapakse, T.C., Nawarathna, R.D. (2021). Pseudoscience Detection Using a Pre-trained Transformer Model with Intelligent ReLabeling. In: Shakya, S., Balas, V.E., Haoxiang, W., Baig, Z. (eds) Proceedings of International Conference on Sustainable Expert Systems. Lecture Notes in Networks and Systems, vol 176. Springer, Singapore. https://doi.org/10.1007/978-981-33-4355-9_25
Download citation
DOI: https://doi.org/10.1007/978-981-33-4355-9_25
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-4354-2
Online ISBN: 978-981-33-4355-9
eBook Packages: EngineeringEngineering (R0)