{ "ok": true, "doi": "10.46243/jst.2022.v7.i09.pp65-82", "doi_display": "10.46243/jst.2022.v7.i09.pp65-82", "doi_url": "https://doi.org/10.46243/jst.2022.v7.i09.pp65-82", "state": "registered", "url": "https://www.jst.org.in/index.php/pub/article/view/903", "title": "A benchmark study of machine learning models for online fake news detection", "version": 2, "registered_via": "crossref", "prefix": { "prefix": "10.46243", "status": "live" }, "registrant": { "name": "Longman Publishers", "kind": "publisher", "country": "India" }, "reserved_at": null, "registered_at": "2026-09-29 22:00:23", "updated_at": "2026-09-29 23:59:41", "withdrawn_at": null, "withdrawn_reason": null, "record": { "format": "smartscholars-doi-metadata/1.0", "doi": "10.46243/jst.2022.v7.i09.pp65-82", "referent": "Creation", "type": "JournalArticle", "structural_type": "Digital", "modes": [ "Visual" ], "characters": [ "Language" ], "titles": [ { "value": "A benchmark study of machine learning models for online fake news detection", "type": "PrincipalTitle", "lang": "en" } ], "identifiers": [ { "type": "DOI", "value": "10.46243/jst.2022.v7.i09.pp65-82" } ], "agents": [ { "role": "author", "name": { "given": "Dr.R VVSV PRASAD", "family": "Dr.R VVSV PRASAD" }, "sequence": "first" }, { "role": "publisher", "name": { "org": "Longman Publishers" } } ], "dates": { "published": "2022-05-11", "date_type": "PublicationDate", "online": "2022-05-11" }, "language": "en", "container": { "type": "Journal", "titles": [ { "value": "Journal of Science & Technology", "type": "PrincipalTitle" } ], "identifiers": [ { "type": "ISSN", "value": "2456-5660", "medium": "electronic" } ], "volume": "7", "issue": "9", "pages": { "first": "65", "last": "82" } }, "links": [ { "url": "https://www.jst.org.in/index.php/pub/article/view/903", "return_type": "text/html", "primary": true }, { "url": "https://www.jst.org.in/index.php/pub/article/download/903/828", "purpose": "text-mining", "return_type": "application/pdf" }, { "url": "https://www.jst.org.in/index.php/pub/article/download/903/1961", "purpose": "text-mining", "return_type": "application/xml" }, { "url": "https://jst.org.in/admin/uploads/new%20jst.pdf", "purpose": "similarity-checking" } ], "abstract": { "value": "The widespread circulation of false information via online platforms is a growing cause for alarm because of the havoc it may wreak. Several machine learning strategies have been proposed for spotting hoaxes. However, the vast majority of them concentrated on a certain category of news (like politics), raising the issue of dataset bias in the used models. Here, we provide the results of a benchmark study that compares three datasets to determine which machine learning technique performs best. To the best of our knowledge, we are the first to investigate and evaluate the performance of many state-of-the- art pre-trained language models for false news detection, alongside the performance of classical and deep learning models. When it comes to detecting false news, we discover that BERT and other comparable pre-trained models perform the best, even when working with a tiny dataset. Because of this, these models are a much superior choice for languages with few electronic contents (i.e., training data). Additionally, we analyzed the models' efficacy, article topics, and article lengths, and shared our findings and insights. We hope that our benchmark study will encourage additional investigation in the field of false news identification and enable news sites and blogs choose the most effective approach.", "lang": "en" }, "license": { "url": "https://creativecommons.org/licenses/by/4.0/", "start": "2022-05-11", "applies_to": "vor" }, "references": [ { "key": "ref1", "doi": "10.1016/j.ins.2019.05.035", "unstructured": "Specifically, Bondielli, A., and F. Marcelloni's work is cited (2019). Techniques for spotting fake news and other forms of Page | 79 propaganda. The reference is to Information Sciences, 497, 38-55. 9 Visit https://www.bbc.com/news/stories-52731624 for more details (last visited October 5, 2020). This item was retrieved on October 5, 2020, from https://www.nature.com/articles/d41586-020-01409-2. \"Rehm, G., P. Bourgonje, and J. M. Schneider\" (2017). A technique for recognizing the inherent bias in titles and abstracts, which aids in the detection of clickbait and fabricated news. To appear in the proceedings of the 2017 EMNLP Workshop on Natural Language Processing and Journalism (pp. 84–89)" }, { "key": "ref2", "unstructured": "Citation Information: Bucilua, C.; Caruana, R.; Niculescu-Mizil, A. (2006). The model's size has been reduced. Knowledge Discovery and Data Mining: The Proceedings of the 12th Annual ACM SIGKDD Conference (pp. 535–541)" }, { "key": "ref3", "doi": "10.1016/b978-012099975-0.50005-1", "unstructured": "Carroll, John D., and Paul Arabie (1998). Multiple-dimensional scaling. Evaluating, judging, and selecting (pp. 179–250). Elsevier" }, { "key": "ref4", "unstructured": "Authors Y. Chen, N. J. Conroy, and V. L. Rubin contributed to its creation (2015). Internet misinformation: recognizing propaganda in the form of clickbait. Workshop on Multimodal Detection of Deceit 2015: Proceedings from the Association for Computing Machinery (pp. 15–19). ACM. The authors (Le, Q. V., Clark, K., Luong, M.-T., and Manning, C. D.) (2020). In order to make text encoders more effective as discriminators than generators, \"Electra\" pre-trains them. This study was previously available on arXiv with the working title 2003.10555" }, { "key": "ref5", "unstructured": "Modest Proposal: A Cliché by M. (2014). An Detector of Sarcasm Read more about the Sarcasm Detector here: http://www.thesarcasmdetector.com/. The authors N. J. Conroy, V. L. Rubin, and Y. Chen (2015). Dishonesty detection algorithms; fake news debunking approaches. Proceedings of the 78th Annual Conference of the Association for Information Science and Technology: Information science with impact: Research in and for the community (p. 82). The American Society for Information Science and Technology" }, { "key": "ref6", "unstructured": "Hovold, J. (2005). Naive Bayes algorithm-based spam detection using word-position features. Semester shared between Europe and Asia Joulin, A., Grave, E., Bojanowski, P., and Mikolov, T. Equipment for properly tagging texts. ArXiv:1607.01759 has a PDF version that you may download" }, { "key": "ref7", "doi": "10.18653/v1/s19-2184", "unstructured": "Lee, Z. Liu, and P. Fung are the authors (2019). Team yeon-de-noising zi's of poorly-labeled data to discover hyperpartisan news won Task 4 at Semeval-2019. The Thirteenth International Workshop on Semantic Evaluation Proceedings The authors are credited as follows: D. Leonhardt and S. A. Thompson. It's no secret that Trump lies. The newest issue of The New York Times is the twentieth. Works by Li, X.; Bing, L.; Zhang, W.; and Lam, W. Sentiment analysis that is both thorough and based on several points of view may be performed with the help of BERT. See the preprint at arXiv:1910.00883" }, { "key": "ref8", "doi": "10.1109/18.61115", "unstructured": "Lin, J. (1991). (1991). (1991). Divergence was calculated using the Shannon entropy. IEEE Trans. Inf. Theor., 37(1), pp. 145–151" }, { "key": "ref9", "unstructured": "Liu, Y. (2019). (2019). Adjust BERT so that it can provide an accurate summary. Refer to the preprint at arXiv: 1903.10318" }, { "key": "ref10", "doi": "10.18653/v1/w19-5006", "unstructured": "Peng, Yan, and Lu, all named Y. For the purpose of determining whether method is best for transfer learning in biomedical natural language processing, we evaluate bert and elmo on 10 gold-standard datasets. You may get the preprint at arXiv:1906.05474" }, { "key": "ref11", "doi": "10.1145/3137597.3137600", "unstructured": "By Shu, Sliva, Wang, Tang, and Liu: Data mining to detect social media hoaxes. This refers to the ACM SIGKDD Explorations Newsletter, volume 19, number 3, pages 22–36" }, { "key": "ref12", "doi": "10.18653/v1/p19-1452", "unstructured": "Ingrid Tenney, Daniel Das, and Elizabeth Pavlick. BERT rediscovers the classic NLP pipeline phases. The preprint may be accessed at arXiv:1905.05950. Authors: John Thorne, Ming Chen, George Myrianthous, Jian Pu, Xiaobo Wang, Antonis Vlachos. Detecting the slant of bogus news stories by using a stacked ensemble of classifiers. To appear in the proceedings of the 2017 EMNLP Workshop on Natural Language Processing and Journalism (pp. 80–83). The name is W. Y. Wang. \"lie, liar, pantless liar\": presenting a new standard dataset for spotting fake news. Obtainable as a PDF file at arXiv:1705.00648" }, { "key": "ref13", "doi": "10.1145/3373464.3373473", "unstructured": "Xiaozhou Zhou and Roberto Zafarani. In order to spot hoaxes that have been widely shared online, a pattern recognition algorithm is being used. Publication information: Explorations, 21(2), 48-60 (Newsletter of the ACM Special Interest Group on Knowledge Discovery in Databases)" } ], "record": { "registrant": "Longman Publishers", "registered": "2024-02-16", "updated": "2026-09-17", "issue_number": 1, "source": "crossref-api", "source_agency": "Crossref (member 25296)" } }, "record_sha256": "c7414888e8e953ba29e0823f1e39a353abb451ba5e5c0effee8fb4efa7e28c8c", "handle": { "synced_at": "2026-10-01 18:12:30", "url": "https://www.jst.org.in/index.php/pub/article/view/903" }, "links": { "record_page": "https://registry.smartscholars.in/record.php?doi=10.46243%2Fjst.2022.v7.i09.pp65-82", "system_metadata": "https://registry.smartscholars.in/resolve.php?doi=10.46243%2Fjst.2022.v7.i09.pp65-82&as=system", "history": "https://registry.smartscholars.in/api.php?action=history&doi=10.46243%2Fjst.2022.v7.i09.pp65-82", "kernel_xml": "https://registry.smartscholars.in/resolve.php?doi=10.46243%2Fjst.2022.v7.i09.pp65-82&as=xml" } }