Abstract
Fake news classification is one of the most interesting problems that has attracted huge attention to the researchers of artificial intelligence, natural language processing, and machine learning (ML). Most of the current works on fake news detection are in the English language, and hence this has limited its widespread usability, especially outside the English literate population. Although there has been a growth in multilingual web content, fake news classification in low-resource languages is still a challenge due to the non-availability of an annotated corpus and tools. This article proposes an effective neural model based on the multilingual Bidirectional Encoder Representations from Transformer (BERT) for domain-agnostic multilingual fake news classification. Large varieties of experiments, including language-specific and domain-specific settings, are conducted. The proposed model achieves high accuracy in domain-specific and domain-agnostic experiments, and it also outperforms the current state-of-the-art models. We perform experiments on zero-shot settings to assess the effectiveness of language-agnostic feature transfer across different languages, showing encouraging results. Cross-domain transfer experiments are also performed to assess language-independent feature transfer of the model. We also offer a multilingual multidomain fake news detection dataset of five languages and seven different domains that could be useful for the research and development in resource-scarce scenarios.
- [1] . 2020. Language-independent fake news detection: English, Portuguese, and Spanish mutual features. Future Internet 12, 5 (2020), 87.
DOI: DOI: https://doi.org/10.3390/fi12050087Google ScholarCross Ref
- [2] . 2018. Deep learning using rectified linear units (ReLU). CoRR abs/1803.08375 (2018).
arxiv:1803.08375 . http://arxiv.org/abs/1803.08375.Google Scholar - [3] . 2016. Many Americans believe fake news is sowing confusion. Pew Research Center 15 (2016), 12.Google Scholar
- [4] . 2017. On the benefit of combining neural, statistical and external features for fake news identification. CoRR abs/1712.03935 (2017).
arxiv:1712.03935 . http://arxiv.org/abs/1712.03935.Google Scholar - [5] . 2018. Universal sentence encoder. CoRR abs/1803.11175 (2018).
arxiv:1803.11175 . http://arxiv.org/abs/1803.11175.Google Scholar - [6] . 2017. Supervised learning of universal sentence representations from natural language inference data. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 670–680.
DOI: DOI: https://doi.org/10.18653/v1/D17-1070Google ScholarCross Ref
- [7] . 2015. Automatic deception detection: Methods for finding fake news. Proceedings of the Association for Information Science and Technology 52, 1 (2015), 1–4.
DOI: DOI: https://doi.org/10.1002/pra2.2015.145052010082Google ScholarCross Ref
- [8] . 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long and Short Papers). 4171–4186.
DOI: DOI: https://doi.org/10.18653/v1/N19-1423Google Scholar - [9] . 1971. Measuring nominal scale agreement among many rater. Psychological Bulletin 76 (1971), 378–382.Google Scholar
Cross Ref
- [10] . 2020. Fake news in the time of COVID-19: Inherent powers over public health. Available at SSRN 3740639 (2020). https://ssrn.com/abstract=3740639 or http://dx.doi.org/10.2139/ssrn.3740639.Google Scholar
- [11] . 2019. Multilingual Fake News Detection with Satire. Retrieved October 17, 2021 from https://halshs.archives-ouvertes.fr/halshs-02391141.Google Scholar
- [12] . 2018. A retrospective analysis of the fake news challenge stance-detection task. In Proceedings of the 27th International Conference on Computational Linguistics. 1859–1874. https://www.aclweb.org/anthology/C18-1158.Google Scholar
- [13] . 2008. Echo Chamber: Rush Limbaugh and the Conservative Media Establishment. Oxford University Press. Google Scholar
- [14] . 2017. RACE: Large-scale ReAding comprehension dataset from examinations. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 785–794.
DOI: DOI: https://doi.org/10.18653/v1/D17-1082Google ScholarCross Ref
- [15] . 1977. The measurement of observer agreement for categorical data. Biometrics 33, 1 (1977), 159–174.Google Scholar
Cross Ref
- [16] . 1998. Confirmation bias: A ubiquitous phenomenon in many guises. Review of General Psychology 2, 2 (1998), 175–220.
DOI: DOI: https://doi.org/10.1037/1089-2680.2.2.175Google ScholarCross Ref
- [17] . 2020. Covid-19 News and Information: Consumption and Attitudes. Results from Week One of Ofcom’s Online Survey. Retrieved October 17, 2021 from https://www.ofcom.org.uk/__data/assets/pdf_file/0031/193747/covid-19-news-consumption-week-one-findings.pdf.Google Scholar
- [18] . 2020. Coronavirus Disease (COVID-19) Advice for the Public: Mythbusters. World Health Organization.Google Scholar
- [19] . 2018. Unsupervised learning of sentence embeddings using compositional n-gram features. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 528–540.
DOI: DOI: https://doi.org/10.18653/v1/N18-1049Google ScholarCross Ref
- [20] . 2018. Automatic detection of fake news. In Proceedings of the 27th International Conference on Computational Linguistics. 3391–3401. https://www.aclweb.org/anthology/C18-1287.Google Scholar
- [21] . 2018. Improving Language Understanding by Generative Pre-Training. Retrieved October 17, 2021 from https://s3-us-west-2.amazonaws.com/openai-assets/researchcovers/languageunsupervised/language understanding paper.pdf.Google Scholar
- [22] . 2016. SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 2383–2392.
DOI: DOI: https://doi.org/10.18653/v1/D16-1264Google ScholarCross Ref
- [23] . 2015. Deception detection for news: Three types of fakes. Proceedings of the Association for Information Science and Technology 52, 1 (2015), 1–4.
DOI: DOI: https://doi.org/10.1002/pra2.2015.145052010083Google ScholarCross Ref
- [24] . 2019. A deep learning approach for automatic detection of fake news. In Proceedings of the 16th International Conference on Natural Language Processing (ICON’19). 230–238. https://cdn.iiit.ac.in/cdn/ltrc.iiit.ac.in/icon2019/icon2019proceedings.pdf.Google Scholar
- [25] . 2017. Fake news detection on social media: A data mining perspective. SIGKDD Explorations Newsletter 19, 1 (
Sept. 2017), 22–36.DOI: DOI: https://doi.org/10.1145/3137597.3137600Google ScholarDigital Library
- [26] . 2017. Fake News Detection on Social Media: A Data Mining Perspective. Retrieved October 17, 2021 from https://doi.org/10.1145/3137597.3137600Google Scholar
- [27] . 2018. FEVER: A large-scale dataset for fact extraction and VERification. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 809–819.
DOI: DOI: https://doi.org/10.18653/v1/N18-1074Google ScholarCross Ref
- [28] . 2017. Attention is all you need. In Advances in Neural Information Processing Systems 30, , , , , , , and (Eds.). Curran Associates Inc., 5998–6008. http://papers.nips.cc/paper/7181-attention-is-all-you-need.pdf.Google Scholar
- [29] . 2018. The spread of true and false news online. Science 359, 6380 (2018), 1146–1151.
DOI: DOI: https://doi.org/10.1126/science.aap9559Google ScholarCross Ref
- [30] . 2019. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In Proceedings of the 7th International Conference on Learning Representations (ICLR’19). https://openreview.net/forum?id=rJ4km2R5t7.Google Scholar
- [31] . 2016. Google’s neural Machine translation system: Bridging the gap between human and machine translation.
arxiv:1609.08144 [cs.CL]Google Scholar - [32] . 2019. Defending against neural fake news. In Advances in Neural Information Processing Systems 32.Google Scholar
Index Terms
A Transformer-Based Approach to Multilingual Fake News Detection in Low-Resource Languages
Recommendations
A Generalized Constraint Approach to Bilingual Dictionary Induction for Low-Resource Language Families
The lack or absence of parallel and comparable corpora makes bilingual lexicon extraction a difficult task for low-resource languages. The pivot language and cognate recognition approaches have been proven useful for inducing bilingual lexicons for such ...
Multilingual Offensive Language Identification for Low-resource Languages
Offensive content is pervasive in social media and a reason for concern to companies and government organizations. Several studies have been recently published investigating methods to detect the various forms of such content (e.g., hate speech, ...
Simple measures of bridging lexical divergence help unsupervised neural machine translation for low-resource languages
AbstractUnsupervised Neural Machine Translation (UNMT) approaches have gained widespread popularity in recent times. Though these approaches show impressive translation performance using only monolingual corpora of the languages involved, these approaches ...






Comments