{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:13:41Z","timestamp":1775229221429,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s10579-024-09787-z","type":"journal-article","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T12:30:13Z","timestamp":1732278613000},"page":"3153-3188","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Fake news article detection datasets for Hindi language"],"prefix":"10.1007","volume":"59","author":[{"given":"Sujit","family":"Kumar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anant","family":"Shankhdhar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Divyam","family":"Singal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvan","family":"Aggarwal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahaan Sameer","family":"Malhotra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanasam","family":"Ranbir Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"9787_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, A., & Dixit, A. (2020). Fake news detection: an ensemble learning approach. In 2020 4th international conference on intelligent computing and control systems (ICICCS) (pp. 1178\u20131183). IEEE.","DOI":"10.1109\/ICICCS48265.2020.9121030"},{"issue":"1","key":"9787_CR2","first-page":"8885861","volume":"2020","author":"I Ahmed","year":"2020","unstructured":"Ahmad, I., Yousaf, M., Yousaf, S., & Ahmad, M. O. (2020). Fake news detection using machine learning ensemble methods. Complexity, 2020(1), 8885861.","journal-title":"Complexity"},{"key":"9787_CR3","doi-asserted-by":"crossref","unstructured":"Ahmed, H., Traore, I., & Saad, S. (2017). Detection of online fake news using n-gram analysis and machine learning techniques. In I. Traore, I. Woungang, & A. Awad (Eds.), Intelligent, secure, and dependable systems in distributed and cloud environments (pp. 127\u2013138). Springer.","DOI":"10.1007\/978-3-319-69155-8_9"},{"issue":"1","key":"9787_CR4","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1002\/spy2.9","volume":"1","author":"H Ahmed","year":"2018","unstructured":"Ahmed, H., Traore, I., & Saad, S. (2018). Detecting opinion spams and fake news using text classification. Security and Privacy, 1(1), 9.","journal-title":"Security and Privacy"},{"key":"9787_CR5","doi-asserted-by":"crossref","unstructured":"Badam, J., Bonagiri, A., Raju, K., & Chakraborty, D. (2022). Aletheia: A fake news detection system for Hindi. In 5th joint international conference on data science & management of data (9th ACM IKDD CODS and 27th COMAD) (pp. 255\u2013259).","DOI":"10.1145\/3493700.3493736"},{"key":"9787_CR6","unstructured":"Bhardwaj, M., Akhtar, M. S., Ekbal, A., Das, A., & Chakraborty, T. (2020). Hostility detection dataset in Hindi. arXiv preprint arXiv:2011.03588"},{"key":"9787_CR7","doi-asserted-by":"crossref","unstructured":"Bhatt, G., Sharma, A., Sharma, S., Nagpal, A., Raman, B., & Mittal, A. (2018). Combining neural, statistical and external features for fake news stance identification. In Companion proceedings of the the web conference 2018 (pp. 1353\u20131357).","DOI":"10.1145\/3184558.3191577"},{"issue":"2","key":"9787_CR8","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1023\/A:1018054314350","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123\u2013140.","journal-title":"Machine Learning"},{"key":"9787_CR9","doi-asserted-by":"crossref","unstructured":"Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM Sigkdd international conference on knowledge discovery and data mining (pp. 785\u2013794).","DOI":"10.1145\/2939672.2939785"},{"key":"9787_CR10","doi-asserted-by":"crossref","unstructured":"Chesney, S., Liakata, M., Poesio, M., & Purver, M. (2017). Incongruent headlines: Yet another way to mislead your readers. In Proceedings of the 2017 Emnlp workshop: Natural language processing meets journalism (pp. 56\u201361).","DOI":"10.18653\/v1\/W17-4210"},{"issue":"4","key":"9787_CR11","first-page":"323","volume":"20","author":"UK Ecker","year":"2014","unstructured":"Ecker, U. K., Lewandowsky, S., Chang, E. P., & Pillai, R. (2014). The effects of subtle misinformation in news headlines. Journal of Experimental Psychology: Applied, 20(4), 323.","journal-title":"Journal of Experimental Psychology: Applied"},{"key":"9787_CR12","doi-asserted-by":"crossref","unstructured":"Fredriksson, T., Mattos, D. I., Bosch, J., & Olsson, H. H. (2020). Data labeling: An empirical investigation into industrial challenges and mitigation strategies. In International conference on product-focused software process improvement (pp. 202\u2013216). Springer.","DOI":"10.1007\/978-3-030-64148-1_13"},{"key":"9787_CR13","doi-asserted-by":"crossref","unstructured":"Fung, Y., Thomas, C., Reddy, R.G., Polisetty, S., Ji, H., Chang, S.-F., McKeown, K., Bansal, M., & Sil, A. (2021). Infosurgeon: Cross-media fine-grained information consistency checking for fake news detection. In Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (Vol. 1: Long Papers, pp. 1683\u20131698).","DOI":"10.18653\/v1\/2021.acl-long.133"},{"key":"9787_CR14","unstructured":"Grave, E., Bojanowski, P., Gupta, P., Joulin, A., & Mikolov, T. (2018). Learning word vectors for 157 languages. In Proceedings of the international conference on language resources and evaluation (LREC 2018)."},{"key":"9787_CR15","unstructured":"Hanselowski, A., PVS, A., Schiller, B., Caspelherr, F., Chaudhuri, D., Meyer, C. M., & Gurevych, I. (2018). A retrospective analysis of the fake news challenge stance detection task. arXiv preprint arXiv:1806.05180"},{"issue":"4","key":"9787_CR16","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/5254.708428","volume":"13","author":"MA Hearst","year":"1998","unstructured":"Hearst, M. A., Dumais, S. T., Osuna, E., Platt, J., & Scholkopf, B. (1998). Support vector machines. IEEE Intelligent Systems and their Applications, 13(4), 18\u201328.","journal-title":"IEEE Intelligent Systems and their Applications"},{"issue":"8","key":"9787_CR17","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735\u20131780.","journal-title":"Neural Computation"},{"issue":"1","key":"9787_CR18","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1609\/icwsm.v12i1.14982","volume":"12","author":"B Horne","year":"2018","unstructured":"Horne, B., Khedr, S., & Adali, S. (2018). Sampling the news producers: A large news and feature data set for the study of the complex media landscape. Proceedings of the International AAAI Conference on Web and Social Media, 12(1), 518\u2013527.","journal-title":"Proceedings of the International AAAI Conference on Web and Social Media"},{"key":"9787_CR19","unstructured":"Hu, J., Ruder, S., Siddhant, A., Neubig, G., Firat, O., & Johnson, M. (2020). Xtreme: A massively multilingual multi-task benchmark for evaluating cross-lingual generalisation. In International conference on machine learning (pp. 4411\u20134421). PMLR."},{"key":"9787_CR20","doi-asserted-by":"crossref","unstructured":"Kakwani, D., Kunchukuttan, A., Golla, S., Gokul, N.C., Bhattacharyya, A., Khapra, M. M. & Kumar, P. (2020). IndicNLPSuite: Monolingual corpora, evaluation benchmarks and pre-trained multilingual language models for Indian languages. In Findings of EMNLP.","DOI":"10.18653\/v1\/2020.findings-emnlp.445"},{"key":"9787_CR21","doi-asserted-by":"crossref","unstructured":"Kumar, S., & Singh, T. D. (2022). Fake news detection on Hindi news dataset. In Global transitions proceedings.","DOI":"10.1016\/j.gltp.2022.03.014"},{"key":"9787_CR22","doi-asserted-by":"crossref","unstructured":"Kumar, S., Kumar, D., Singh, S. R. (2023). Gated recursive and sequential deep hierarchical encoding for detecting incongruent news articles. IEEE Transactions on Computational Social Systems.","DOI":"10.1109\/TCSS.2023.3247445"},{"issue":"1","key":"9787_CR23","doi-asserted-by":"crossref","first-page":"1575365","DOI":"10.1155\/2022\/1575365","volume":"2022","author":"S Mishra","year":"2022","unstructured":"Mishra, S., Shukla, P., & Agarwal, R. (2022). Analyzing machine learning enabled fake news detection techniques for diversified datasets. Wireless Communications and Mobile Computing, 2022(1), 1575365.","journal-title":"Wireless Communications and Mobile Computing"},{"issue":"2","key":"9787_CR24","doi-asserted-by":"publisher","first-page":"205630512110090","DOI":"10.1177\/20563051211009013","volume":"7","author":"TA Neyazi","year":"2021","unstructured":"Neyazi, T. A., Kalogeropoulos, A., & Nielsen, R. K. (2021). Misinformation concerns and online news participation among internet users in India. Social Media + Society, 7(2), 20563051211009012.","journal-title":"Social Media + Society"},{"key":"9787_CR25","doi-asserted-by":"crossref","unstructured":"Ngada, O., & Haskins, B. (2020). Fake news detection using content-based features and machine learning. In 2020 IEEE Asia-Pacific conference on computer science and data engineering (CSDE) (pp. 1\u20136). IEEE.","DOI":"10.1109\/CSDE50874.2020.9411638"},{"key":"9787_CR26","doi-asserted-by":"crossref","unstructured":"Pappagari, R., Zelasko, P., Villalba, J., Carmiel, Y., & Dehak, N. (2019). Hierarchical transformers for long document classification. In 2019 IEEE automatic speech recognition and understanding workshop (ASRU) (pp. 838\u2013844). IEEE.","DOI":"10.1109\/ASRU46091.2019.9003958"},{"key":"9787_CR27","doi-asserted-by":"crossref","unstructured":"Patwa, P., Bhardwaj, M., Guptha, V., Kumari, G., Sharma, S., Pykl, S., Das, A., Ekbal, A., Akhtar, M. S., & Chakraborty, T. (2021). Overview of constraint 2021 shared tasks: Detecting English covid-19 fake news and hindi hostile posts. In International workshop on combating online hostile posts in regional languages during emergency situation (pp. 42\u201353). Springer.","DOI":"10.1007\/978-3-030-73696-5_5"},{"key":"9787_CR28","doi-asserted-by":"crossref","unstructured":"Pomerleau, D., & Rao, D. (2021). Exploring summarization to enhance headline stance detection. In V. E. M\u00e9tais, F. Meziane, H. Horacek, & E. Kapetanios (Eds.), NLDB 2021. Natural language processing and information systems (Vol. 12801, pp. 243\u2013254). Springer.","DOI":"10.1007\/978-3-030-80599-9_22"},{"key":"9787_CR29","doi-asserted-by":"crossref","unstructured":"Qi, P., Zhang, Y., Zhang, Y., Bolton, J., & Manning, C. D. (2020). Stanza: A python natural language processing toolkit for many human languages. arXiv preprint arXiv:2003.07082.","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"key":"9787_CR30","unstructured":"Quinlan, J. R. (1996). Bagging, boosting, and c4. 5. In Aaai\/Iaai (Vol. 1, pp. 725\u2013730)."},{"key":"9787_CR31","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1023\/A:1022643204877","volume":"1","author":"JR Quinlan","year":"1986","unstructured":"Quinlan, J. R. (1986). Induction of decision trees. Machine Learning, 1, 81\u2013106.","journal-title":"Machine Learning"},{"key":"9787_CR32","unstructured":"Riedel, B., Augenstein, I., Spithourakis, G. P., & Riedel, S. (2017). A simple but tough-to-beat baseline for the fake news challenge stance detection task. arXiv preprint arXiv:1707.03264."},{"issue":"4","key":"9787_CR33","doi-asserted-by":"publisher","first-page":"1328","DOI":"10.1109\/TKDE.2019.2946162","volume":"33","author":"Y Roh","year":"2019","unstructured":"Roh, Y., Heo, G., & Whang, S. E. (2019). A survey on data collection for machine learning: A big data-ai integration perspective. IEEE Transactions on Knowledge and Data Engineering, 33(4), 1328\u20131347.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"9787_CR34","unstructured":"Schapire, R. E. (1999). A brief introduction to boosting. In Ijcai (Vol. 99, pp. 1401\u20131406)."},{"key":"9787_CR35","doi-asserted-by":"crossref","unstructured":"Schapire, R. E. (2013). Explaining adaboost. In Empirical inference: festschrift in honor of vladimir N. Vapnik (pp. 37\u201352). Berlin, Heidelberg: Springer Berlin Heidelberg.","DOI":"10.1007\/978-3-642-41136-6_5"},{"key":"9787_CR36","doi-asserted-by":"crossref","unstructured":"Sun, D. Q., Kotek, H., Klein, C., Gupta, M., Li, W., & Williams, J. D. (2020). Improving human-labeled data through dynamic automatic conflict resolution. In Proceedings of the 28th international conference on computational linguistics (pp. 3547\u20133557).","DOI":"10.18653\/v1\/2020.coling-main.316"},{"key":"9787_CR37","unstructured":"Tang, Y., Tran, C., Li, X., Chen, P.-J., Goyal, N., Chaudhary, V., Gu, J., & Fan, A. (2020). Multilingual translation with extensible multilingual pretraining and finetuning. arXiv:2008.00401 [cs.CL]."},{"key":"9787_CR38","doi-asserted-by":"publisher","unstructured":"Thorne, J., Chen, M., Myrianthous, G., Pu, J., Wang, X., & Vlachos, A. (2017). Fake news stance detection using stacked ensemble of classifiers. In Proceedings of the 2017 EMNLP workshop: Natural language processing meets journalism (pp. 80\u201383). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/W17-4214.","DOI":"10.18653\/v1\/W17-4214"},{"key":"9787_CR39","doi-asserted-by":"crossref","unstructured":"Thorne, J., Vlachos, A., Christodoulopoulos, C., & Mittal, A. (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 (Vol. 1 (Long Papers), pp. 809\u2013819).","DOI":"10.18653\/v1\/N18-1074"},{"key":"9787_CR40","unstructured":"Vaswani, A. (2017). Attention is all you need. Advances in Neural Information Processing Systems."},{"key":"9787_CR41","doi-asserted-by":"crossref","unstructured":"Wynne, H. E., & Wint, Z. Z. (2019). Content based fake news detection using n-gram models. In Proceedings of the 21st international conference on information integration and web-based applications & services (pp. 669\u20136730.","DOI":"10.1145\/3366030.3366116"},{"issue":"01","key":"9787_CR42","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1609\/aaai.v33i01.3301791","volume":"33","author":"S Yoon","year":"2019","unstructured":"Yoon, S., Park, K., Shin, J., Lim, H., Won, S., Cha, M., & Jung, K. (2019). Detecting incongruity between news headline and body text via a deep hierarchical encoder. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 791\u2013800.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-024-09787-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10579-024-09787-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-024-09787-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T00:47:30Z","timestamp":1757119650000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10579-024-09787-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"references-count":42,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["9787"],"URL":"https:\/\/doi.org\/10.1007\/s10579-024-09787-z","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"value":"1574-020X","type":"print"},{"value":"1574-0218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"17 October 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no Conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}