{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T06:29:50Z","timestamp":1774074590813,"version":"3.50.1"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T00:00:00Z","timestamp":1756339200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T00:00:00Z","timestamp":1756339200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soc. Netw. Anal. Min."],"DOI":"10.1007\/s13278-025-01505-z","type":"journal-article","created":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T08:58:39Z","timestamp":1756371519000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Addressing data scarcity in multilingual fake news detection: an LLM-based dataset augmentation approach"],"prefix":"10.1007","volume":"15","author":[{"given":"Razieh","family":"Chalehchaleh","sequence":"first","affiliation":[]},{"given":"Reza","family":"Farahbakhsh","sequence":"additional","affiliation":[]},{"given":"Noel","family":"Crespi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,28]]},"reference":[{"key":"1505_CR1","unstructured":"Ahlb\u00e4ck E, Dougly M (2023) Can large language models enhance fake news detection?: Improving fake news detection with data augmentation"},{"issue":"17","key":"1505_CR2","doi-asserted-by":"publisher","first-page":"51009","DOI":"10.1007\/s11042-023-17470-8","volume":"83","author":"J Alghamdi","year":"2024","unstructured":"Alghamdi J, Luo S, Lin Y (2024) A comprehensive survey on machine learning approaches for fake news detection. Multimed Tools Appl 83(17):51009\u201351067","journal-title":"Multimed Tools Appl"},{"issue":"2","key":"1505_CR3","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1257\/jep.31.2.211","volume":"31","author":"H Allcott","year":"2017","unstructured":"Allcott H, Gentzkow M (2017) Social media and fake news in the 2016 election. J Econ Perspect 31(2):211\u2013236","journal-title":"J Econ Perspect"},{"key":"1505_CR4","doi-asserted-by":"crossref","unstructured":"Alnabhan MQ, Branco P (2024) Fake news detection using deep learning: a systematic literature review. IEEE Access","DOI":"10.1109\/ACCESS.2024.3435497"},{"issue":"5","key":"1505_CR5","doi-asserted-by":"publisher","first-page":"73","DOI":"10.3390\/socsci9050073","volume":"9","author":"S Alonso Garc\u00eda","year":"2020","unstructured":"Alonso Garc\u00eda S, G\u00f3mez Garc\u00eda G, Sanz Prieto M et al (2020) The impact of term fake news on the scientific community scientific performance and mapping in web of science. Soc Sci 9(5):73","journal-title":"Soc Sci"},{"key":"1505_CR6","unstructured":"Amjad M, Sidorov G, Zhila A (2020) Data augmentation using machine translation for fake news detection in the Urdu language. In: Proceedings of the twelfth language resources and evaluation conference, pp 2537\u20132542"},{"key":"1505_CR7","doi-asserted-by":"crossref","unstructured":"Anderson KJ (2024) What is news? exploring differences in how younger and older cohorts use news in today\u2019s media environment. Commun Res Practice pp 1\u201321","DOI":"10.1080\/22041451.2024.2344997"},{"key":"1505_CR8","unstructured":"Ashraf N, Butt S, Sidorov G, et\u00a0al (2021) CIC at checkthat! 2021: Fake news detection using machine learning and data augmentation. In: CLEF (Working Notes), pp 446\u2013454"},{"key":"1505_CR9","doi-asserted-by":"crossref","unstructured":"Bashardoust A, Feuerriegel S, Shrestha YR (2024) Comparing the willingness to share for human-generated vs. ai-generated fake news. Proceedings of the ACM on Human-Computer Interaction 8(CSCW2):1\u201321","DOI":"10.1145\/3687028"},{"issue":"7","key":"1505_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3544558","volume":"55","author":"M Bayer","year":"2022","unstructured":"Bayer M, Kaufhold MA, Reuter C (2022) A survey on data augmentation for text classification. ACM Comput Surv 55(7):1\u201339","journal-title":"ACM Comput Surv"},{"key":"1505_CR11","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877\u20131901","journal-title":"Adv Neural Inf Process Syst"},{"key":"1505_CR12","doi-asserted-by":"crossref","unstructured":"Chalehchaleh R, Farahbakhsh R, Crespi N (2024) Multilingual fake news detection: a study on various models and training scenarios. In: Intelligent System Conference, Springer, pp 73\u201389","DOI":"10.1007\/978-3-031-66428-1_5"},{"key":"1505_CR13","first-page":"258","volume-title":"Complex Netw Appl XIII","author":"R Chalehchaleh","year":"2025","unstructured":"Chalehchaleh R, Farahbakhsh R, Crespi N (2025) Enhancing multilingual fake news detection through LLM-based data augmentation. Complex Netw Appl XIII. Springer Nature, Switzerland, Cham, pp 258\u2013270"},{"key":"1505_CR14","unstructured":"Chiang WL, Li Z, Lin Z, et\u00a0al (2023) Vicuna: an open-source Chatbot impressing GPT-4 with 90%* ChatGPT Quality|LMSYS Org. https:\/\/lmsys.org\/blog\/2023-03-30-vicuna"},{"issue":"1","key":"1505_CR15","first-page":"1","volume":"21","author":"A De","year":"2021","unstructured":"De A, Bandyopadhyay D, Gain B et al (2021) A transformer-based approach to multilingual fake news detection in low-resource languages. Trans Asian Low-Resour Lang Inf Process 21(1):1\u201320","journal-title":"Trans Asian Low-Resour Lang Inf Process"},{"key":"1505_CR16","unstructured":"Devlin J, Chang MW, Lee K, et\u00a0al (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"key":"1505_CR17","doi-asserted-by":"publisher","unstructured":"Ding B, Qin C, Zhao R, et\u00a0al (2024) Data augmentation using LLMs: Data perspectives, learning paradigms and challenges. In: Ku LW, Martins A, Srikumar V (eds) Findings of the Association for Computational Linguistics: ACL 2024. Association for Computational Linguistics, Bangkok, Thailand, pp 1679\u20131705. https:\/\/doi.org\/10.18653\/v1\/2024.findings-acl.97","DOI":"10.18653\/v1\/2024.findings-acl.97"},{"key":"1505_CR18","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.518","volume":"7","author":"A D\u2019Ulizia","year":"2021","unstructured":"D\u2019Ulizia A, Caschera MC, Ferri F et al (2021) Fake news detection: a survey of evaluation datasets. Peer J Comput Sci 7:e518","journal-title":"Peer J Comput Sci"},{"issue":"11","key":"1505_CR19","doi-asserted-by":"publisher","first-page":"1818","DOI":"10.1038\/s41562-023-01726-2","volume":"7","author":"S Feuerriegel","year":"2023","unstructured":"Feuerriegel S, DiResta R, Goldstein JA et al (2023) Research can help to tackle AI-generated disinformation. Nat Hum Behav 7(11):1818\u20131821","journal-title":"Nat Hum Behav"},{"issue":"1","key":"1505_CR20","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s12599-023-00834-7","volume":"66","author":"S Feuerriegel","year":"2024","unstructured":"Feuerriegel S, Hartmann J, Janiesch C et al (2024) Generative aI. Bus Inf Syst Eng 66(1):111\u2013126","journal-title":"Bus Inf Syst Eng"},{"issue":"6","key":"1505_CR21","doi-asserted-by":"publisher","first-page":"455","DOI":"10.2471\/BLT.20.276782","volume":"99","author":"E Gabarron","year":"2021","unstructured":"Gabarron E, Oyeyemi SO, Wynn R (2021) Covid-19-related misinformation on social media: a systematic review. Bull World Health Organ 99(6):455","journal-title":"Bull World Health Organ"},{"issue":"6425","key":"1505_CR22","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1126\/science.aau2706","volume":"363","author":"N Grinberg","year":"2019","unstructured":"Grinberg N, Joseph K, Friedland L et al (2019) Fake news on twitter during the 2016 US presidential election. Science 363(6425):374\u2013378","journal-title":"Science"},{"key":"1505_CR23","doi-asserted-by":"crossref","unstructured":"Hamed SK, Ab\u00a0Aziz MJ, Yaakub MR (2023) A review of fake news detection approaches: a critical analysis of relevant studies and highlighting key challenges associated with the dataset, feature representation, and data fusion. Heliyon","DOI":"10.1016\/j.heliyon.2023.e20382"},{"key":"1505_CR24","doi-asserted-by":"publisher","unstructured":"Honnibal M, Montani I, Van\u00a0Landeghem S, et\u00a0al (2020) Spacy: industrial-strength natural language processing in pytho. https:\/\/doi.org\/10.5281\/zenodo.1212303","DOI":"10.5281\/zenodo.1212303"},{"key":"1505_CR25","doi-asserted-by":"publisher","unstructured":"Hu B, Sheng Q, Cao J, et\u00a0al (2024) Bad actor, good advisor: exploring the role of large language models in fake news detection. In: Proceedings of the AAAI conference on Artificial Intelligence, pp 22105\u201322113. https:\/\/doi.org\/10.1609\/aaai.v38i20.30214","DOI":"10.1609\/aaai.v38i20.30214"},{"key":"1505_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110125","volume":"136","author":"J Hua","year":"2023","unstructured":"Hua J, Cui X, Li X et al (2023) Multimodal fake news detection through data augmentation-based contrastive learning. Appl Soft Comput 136:110125","journal-title":"Appl Soft Comput"},{"issue":"12","key":"1505_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji Z, Lee N, Frieske R et al (2023) Survey of hallucination in natural language generation. ACM Comput Surv 55(12):1\u201338","journal-title":"ACM Comput Surv"},{"key":"1505_CR28","unstructured":"J\u00fanior WO, da\u00a0Cruz MS, Wyzykowski ABV, et\u00a0al (2022) The use of data augmentation as a technique for improving neural network accuracy in detecting fake news about Covid-19. arXiv preprint arXiv:2205.00452"},{"key":"1505_CR29","unstructured":"Kalogeropoulos A, et\u00a0al (2019) How younger generations consume news differently. Reuters Institute Digital News Report pp 54\u201359"},{"key":"1505_CR30","doi-asserted-by":"publisher","first-page":"31538","DOI":"10.1109\/ACCESS.2024.3369918","volume":"12","author":"J Kapusta","year":"2024","unstructured":"Kapusta J, Dr\u017e\u00edk D, \u0160teflovi\u010d K et al (2024) Text data augmentation techniques for word embeddings in fake news classification. IEEE Access 12:31538\u201331550","journal-title":"IEEE Access"},{"issue":"17","key":"1505_CR31","doi-asserted-by":"publisher","first-page":"8398","DOI":"10.3390\/app12178398","volume":"12","author":"AJ Keya","year":"2022","unstructured":"Keya AJ, Wadud MAH, Mridha M et al (2022) Augfake-Bert: handling imbalance through augmentation of fake news using Bert to enhance the performance of fake news classification. Appl Sci 12(17):8398","journal-title":"Appl Sci"},{"key":"1505_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122778","volume":"244","author":"AA Khan","year":"2024","unstructured":"Khan AA, Chaudhari O, Chandra R (2024) A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation. Expert Syst Appl 244:122778","journal-title":"Expert Syst Appl"},{"key":"1505_CR33","unstructured":"Kuntur S, Wr\u00f3blewska A, Paprzycki M, et\u00a0al (2024) Fake news detection: It\u2019s all in the data! arXiv preprint arXiv:2407.02122"},{"key":"1505_CR34","doi-asserted-by":"crossref","unstructured":"Li Y, Jiang B, Shu K, et\u00a0al (2020) Mm-covid: a multilingual and multimodal data repository for combating Covid-19 disinformation. arXiv preprint arXiv:2011.04088","DOI":"10.1109\/BigData50022.2020.9378472"},{"issue":"9","key":"1505_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3560815","volume":"55","author":"P Liu","year":"2023","unstructured":"Liu P, Yuan W, Fu J et al (2023) Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput Surv 55(9):1\u201335","journal-title":"ACM Comput Surv"},{"key":"1505_CR36","unstructured":"Liu Y, Ott M, Goyal N, et\u00a0al (2019) Roberta: a robustly optimized Bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"key":"1505_CR37","unstructured":"Minaee S, Mikolov T, Nikzad N, et\u00a0al (2024) Large language models: a survey. arXiv preprint arXiv:2402.06196"},{"issue":"2","key":"1505_CR38","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/s10796-022-10242-z","volume":"26","author":"F Olan","year":"2024","unstructured":"Olan F, Jayawickrama U, Arakpogun EO et al (2024) Fake news on social media: the impact on society. Inf Syst Front 26(2):443\u2013458","journal-title":"Inf Syst Front"},{"key":"1505_CR39","unstructured":"Paszke A, Gross S, Massa F, et\u00a0al (2019) Pytorch: an imperative style, high-performance deep learning library. arXiv:1912.01703"},{"key":"1505_CR40","doi-asserted-by":"crossref","unstructured":"Pierri F, Luceri L, Jindal N, et\u00a0al (2023) Propaganda and misinformation on facebook and twitter during the Russian invasion of Ukraine. In: Proceedings of the 15th ACM web science conference 2023, pp 65\u201374","DOI":"10.1145\/3578503.3583597"},{"key":"1505_CR41","doi-asserted-by":"publisher","unstructured":"Reimers N, Gurevych I (2019) Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Inui K, Jiang J, Ng V, et\u00a0al (eds) Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, pp 3982\u2013399. https:\/\/doi.org\/10.18653\/v1\/D19-1410","DOI":"10.18653\/v1\/D19-1410"},{"key":"1505_CR42","doi-asserted-by":"crossref","unstructured":"Rocha YM, De\u00a0Moura GA, Desid\u00e9rio GA, et\u00a0al (2021) The impact of fake news on social media and its influence on health during the covid-19 pandemic: a systematic review. J Public Health pp 1\u201310","DOI":"10.1007\/s10389-021-01658-z"},{"issue":"2","key":"1505_CR43","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1145\/3624724","volume":"67","author":"M Shanahan","year":"2024","unstructured":"Shanahan M (2024) Talking about large language models. Commun ACM 67(2):68\u201379","journal-title":"Commun ACM"},{"issue":"4","key":"1505_CR44","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1080\/10350330.2021.1929147","volume":"33","author":"K Sipitanos","year":"2023","unstructured":"Sipitanos K (2023) Raising awareness against fake news to protect democracy: the myth of islamophobia in trump\u2019s speech. Soc Semiot 33(4):714\u2013730","journal-title":"Soc Semiot"},{"key":"1505_CR45","unstructured":"St. Aubin C, Liedke J (2024) News platform fact sheet. https:\/\/pewrsr.ch\/3EVRmdU"},{"key":"1505_CR46","doi-asserted-by":"crossref","unstructured":"Tomassi A, Falegnami A, Romano E (2024) Mapping automatic social media information disorder. The role of bots and AI in spreading misleading information in society. PLoS ONE 19(5):e0303183","DOI":"10.1371\/journal.pone.0303183"},{"key":"1505_CR47","unstructured":"Touvron H, Lavril T, Izacard G, et\u00a0al (2023a) Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971"},{"key":"1505_CR48","unstructured":"Touvron H, Martin L, Stone K, et\u00a0al (2023b) Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288"},{"key":"1505_CR49","doi-asserted-by":"crossref","unstructured":"S\u00e1nchez\u00a0del Vas R, Tu\u00f1\u00f3n\u00a0Navarro J (2024) Disinformation on the covid-19 pandemic and the Russia\u2013Ukraine war: two sides of the same coin? Hum Soc Sci Commun 11(1)","DOI":"10.1057\/s41599-024-03355-0"},{"key":"1505_CR50","unstructured":"Vaswani A, Shazeer N, Parmar N, et\u00a0al (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"issue":"3","key":"1505_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3386252","volume":"53","author":"Y Wang","year":"2020","unstructured":"Wang Y, Yao Q, Kwok JT et al (2020) Generalizing from a few examples: a survey on few-shot learning. ACM Comput Surv (CSUR) 53(3):1\u201334","journal-title":"ACM Comput Surv (CSUR)"},{"key":"1505_CR52","unstructured":"Wang Z, Wang P, Liu K, et\u00a0al (2024) A comprehensive survey on data augmentation. arXiv preprint arXiv:2405.09591"},{"key":"1505_CR53","doi-asserted-by":"publisher","unstructured":"Wolf T, Debut L, Sanh V, et\u00a0al (2020) Transformers: state-of-the-art natural language processing. In: Liu Q, Schlangen D (eds) Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations. Association for computational linguistics, Online, pp 38\u201345.https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-demos.6","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"1505_CR54","unstructured":"Wu Y, Xiao Y, Hu M, et\u00a0al (2024) Towards robust evidence-aware fake news detection via improving semantic perception. In: Proceedings of the 2024 joint international conference on computational linguistics, language resources and evaluation (LREC-COLING 2024), pp 16607\u201316618"},{"issue":"6","key":"1505_CR55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3653304","volume":"18","author":"J Yang","year":"2024","unstructured":"Yang J, Jin H, Tang R et al (2024) Harnessing the power of LLMs in practice: a survey on chatgpt and beyond. ACM Trans Knowl Discov Data 18(6):1\u201332","journal-title":"ACM Trans Knowl Discov Data"},{"key":"1505_CR56","unstructured":"Zhang J, Zhao Y, Saleh M, et\u00a0al (2020) Pegasus: pre-training with extracted gap-sentences for abstractive summarization. In: International conference on machine learning, PMLR, pp 11328\u201311339"},{"key":"1505_CR57","unstructured":"Zhao WX, Zhou K, Li J, et\u00a0al (2023) A survey of large language models. arXiv preprint arXiv:2303.18223"}],"container-title":["Social Network Analysis and Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13278-025-01505-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13278-025-01505-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13278-025-01505-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T08:28:16Z","timestamp":1765960096000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13278-025-01505-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,28]]},"references-count":57,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1505"],"URL":"https:\/\/doi.org\/10.1007\/s13278-025-01505-z","relation":{},"ISSN":["1869-5469"],"issn-type":[{"value":"1869-5469","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,28]]},"assertion":[{"value":"30 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 July 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"92"}}