{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T21:55:20Z","timestamp":1781646920588,"version":"3.54.5"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100015068","name":"Universidade de Santiago de Compostela","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100015068","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Cyberbullying has experienced a surge in recent years, mainly due to the widespread adoption of social media platforms. This trend manifests in multiple ways, with hostile language being one of the most common. The latter underscores the urgent need for robust detection methods to address this issue effectively. To address this problem, we propose a novel pipeline to enhance hostile language detection in social media. Our approach consists of a combination of two ideas: First, we propose conducting a Domain Adaptation procedure to specialize the knowledge of a pre-trained BERT, making it more specialized in the domain of social media. For this adaptation, we modify the traditional random Masked Language Modeling technique and propose three novel strategies for selecting the subset of tokens to mask out cleverly. Second, we tailor an Adversarial Regularizer when fine-tuning the adapted BERT for specific hostile-language datasets. We evaluate the performance of our method for detecting hate speech, aggressiveness, offensiveness, and sexism. Our results show that the Domain Adaptation procedure significantly outperforms vanilla BERT, and the Adversarial Regularizer can lead to more robust fine-tuning, thereby enhancing performance. Moreover, we demonstrate that these methods can be used together to achieve an even more significant performance boost.<\/jats:p>","DOI":"10.1007\/s11042-026-21521-1","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T14:53:45Z","timestamp":1774968825000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Clever domain adaptation strategies for BERT in the task of hostile-language detection"],"prefix":"10.1007","volume":"85","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4998-7929","authenticated-orcid":false,"given":"Emilio","family":"Villa-Cueva","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8213-957X","authenticated-orcid":false,"given":"Mario Ezra","family":"Arag\u00f3n","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1018-4221","authenticated-orcid":false,"given":"Adri\u00e1n Pastor","family":"L\u00f3pez-Monroy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8533-2818","authenticated-orcid":false,"given":"Fernando","family":"S\u00e1nchez-Vega","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"key":"21521_CR1","unstructured":"Ortiz-Ospina E (2019) The rise of social media. Our world in data. https:\/\/ourworldindata.org\/rise-of-social-media"},{"issue":"S2","key":"21521_CR2","doi-asserted-by":"publisher","first-page":"195","DOI":"10.2105\/ajph.2011.300608","volume":"102","author":"DD Luxton","year":"2012","unstructured":"Luxton DD, June JD, Fairall JM (2012) Social media and suicide: A public health perspective. Am J Public Health 102(S2):195\u2013200. https:\/\/doi.org\/10.2105\/ajph.2011.300608","journal-title":"Am J Public Health"},{"key":"21521_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122807","volume":"242","author":"Z Zhao","year":"2024","unstructured":"Zhao Z, Alzubaidi L, Zhang J, Duan Y, Gu Y (2024) A comparison review of transfer learning and self-supervised learning: Definitions, applications, advantages and limitations. Expert Syst Appl 242:122807. https:\/\/doi.org\/10.1016\/j.eswa.2023.122807","journal-title":"Expert Syst Appl"},{"key":"21521_CR4","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. In: Burstein J, Doran C, Solorio T (eds) 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). Association for Computational Linguistics, Minneapolis, Minnesota, pp 4171\u20134186. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"21521_CR5","unstructured":"Radford A, Narasimhan K (2018) Improving language understanding by generative pre-training. https:\/\/api.semanticscholar.org\/CorpusID:49313245"},{"key":"21521_CR6","doi-asserted-by":"crossref","unstructured":"Han X, Eisenstein J (2019) Unsupervised domain adaptation of contextualized embeddings for sequence labeling","DOI":"10.18653\/v1\/D19-1433"},{"key":"21521_CR7","doi-asserted-by":"publisher","unstructured":"Gururangan S, Marasovi\u0107 A, Swayamdipta S, Lo K, Beltagy I, Downey D, Smith NA (2020) Don\u2019t stop pretraining: Adapt language models to domains and tasks. In: Jurafsky D, Chai J, Schluter N, Tetreault J (eds) Proceedings of the 58th annual meeting of the association for computational linguistics. Association for Computational Linguistics, Online, pp 8342\u20138360. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.740","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"21521_CR8","doi-asserted-by":"publisher","unstructured":"Noorian Z, Ghenai A, Moradisani H, Zarrinkalam F, Alavijeh SZ (2024) User-centric modeling of online hate through the lens of psycholinguistic patterns and behaviors in social media. IEEE Trans Comput Soc Syst 1\u201313. https:\/\/doi.org\/10.1109\/TCSS.2024.3359010","DOI":"10.1109\/TCSS.2024.3359010"},{"issue":"1","key":"21521_CR9","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1109\/TCSS.2023.3252401","volume":"11","author":"MR Awal","year":"2024","unstructured":"Awal MR, Lee RK-W, Tanwar E, Garg T, Chakraborty T (2024) Model-agnostic meta-learning for multilingual hate speech detection. IEEE Trans Comput Soc Syst 11(1):1086\u20131095. https:\/\/doi.org\/10.1109\/TCSS.2023.3252401","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"21521_CR10","doi-asserted-by":"publisher","unstructured":"Ahmed U, Lin JC-W (2022) Deep explainable hate speech active learning on social-media data. IEEE Trans Comput Soc Syst 1\u201311. https:\/\/doi.org\/10.1109\/TCSS.2022.3165136","DOI":"10.1109\/TCSS.2022.3165136"},{"issue":"1","key":"21521_CR11","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1109\/TCSS.2022.3230974","volume":"11","author":"K Maity","year":"2024","unstructured":"Maity K, Sen T, Saha S, Bhattacharyya P (2024) Mtbullygnn: A graph neural network-based multitask framework for cyberbullying detection. IEEE Trans Comput Soc Syst 11(1):849\u2013858. https:\/\/doi.org\/10.1109\/TCSS.2022.3230974","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"21521_CR12","unstructured":"Bhattacharya S, Singh S, Kumar R, Bansal A, Bhagat A, Dawer Y, Lahiri B, Ojha AK (2020) Developing a multilingual annotated corpus of misogyny and aggression. In: Proceedings of the second workshop on trolling, aggression and cyberbullying. European Language Resources Association (ELRA), Marseille, France, pp 158\u2013168. https:\/\/www.aclweb.org\/anthology\/2020.trac2-1.25"},{"key":"21521_CR13","unstructured":"Sigurbergsson GI, Derczynski L (2020) Offensive language and hate speech detection for Danish. In: Proceedings of the twelfth language resources and evaluation conference. European Language Resources Association, Marseille, France, pp 3498\u20133508. https:\/\/aclanthology.org\/2020.lrec-1.430"},{"key":"21521_CR14","unstructured":"Mubarak H, Darwish K, Magdy W, Elsayed T, Al-Khalifa H (2020) Overview of OSACT4 Arabic offensive language detection shared task. In: Proceedings of the 4th workshop on open-source arabic corpora and processing tools, with a shared task on offensive language detection. European Language Resource Association, Marseille, France, pp 48\u201352. https:\/\/aclanthology.org\/2020.osact-1.7"},{"key":"21521_CR15","doi-asserted-by":"publisher","unstructured":"Basile V, Bosco C, Fersini E, Nozza D, Patti V, Pardo FMR, Rosso P, Sanguinetti M (2019) SemEval-2019 task 5: Multilingual detection of hate speech against immigrants and women in twitter. In: Proceedings of the 13th international workshop on semantic evaluation. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/s19-2007","DOI":"10.18653\/v1\/s19-2007"},{"key":"21521_CR16","unstructured":"Nations U: What is hate speech? | United Nations \u2014 un.org. https:\/\/www.un.org\/en\/hate-speech\/understanding-hate-speech\/what-is-hate-speech. Accessed 05 May 2023"},{"key":"21521_CR17","unstructured":"Arag\u00f3n ME, Jarqu\u00edn-V\u00e1squez HJ, Montes-y-G\u00f3mez M, Escalante HJ, Pineda LV, G\u00f3mez-Adorno H, Posadas-Dur\u00e1n JPF, Bel-Enguix G (2020) Overview of mex-a3t at iberlef 2020: Fake news and aggressiveness analysis in mexican spanish. In: IberLEF@SEPLN"},{"key":"21521_CR18","unstructured":"Aggressive. Houghton mifflin harcourt publishing company. https:\/\/dictionary.cambridge.org\/dictionary\/english\/aggressive Accessed 04 May 2023"},{"key":"21521_CR19","unstructured":"Plaza-del-Arco FM, Casavantes M, Escalante HJ, Mart\u00edn\u00a0Valdivia MT, Montejo\u00a0R\u00e1ez A, G\u00f3mez M, Jarqu\u00edn-V\u00e1squez H, Pineda L (2021) Overview of MeOffendEs at IberLEF 2021: Offensive Language Detection in Spanish Variants"},{"key":"21521_CR20","unstructured":"Offensive. https:\/\/dictionary.cambridge.org\/dictionary\/english\/aggressive Accessed 04 May 2023"},{"key":"21521_CR21","first-page":"195","volume":"67","author":"F Rodr\u00edguez-S\u00e1nchez","year":"2021","unstructured":"Rodr\u00edguez-S\u00e1nchez F, Carrillo-de-Albornoz J, Plaza L, Gonzalo J, Rosso P, Comet M, Donoso T (2021) Overview of EXIST 2021: sEXism Identification in Social neTworks. Procesamiento del Lenguaje Natural 67:195\u2013207","journal-title":"Procesamiento del Lenguaje Natural"},{"key":"21521_CR22","doi-asserted-by":"publisher","unstructured":"P\u00e9rez JM, Luque FM (2019) Atalaya at SemEval 2019 task 5: Robust embeddings for tweet classification. In: Proceedings of the 13th international workshop on semantic evaluation. Association for Computational Linguistics, Minneapolis, Minnesota, USA, pp 64\u201369. https:\/\/doi.org\/10.18653\/v1\/S19-2008","DOI":"10.18653\/v1\/S19-2008"},{"key":"21521_CR23","unstructured":"Guzman-Silverio M, Balderas-Paredes \u00c1, L\u00f3pez-Monroy AP (2020) Transformers and data augmentation for aggressiveness detection in mexican Spanish. In: IberLEF@SEPLN"},{"key":"21521_CR24","unstructured":"G\u00f3mez-Espinosa V, niz-S\u00e1nchez VM, L\u00f3pez-Monroy AP (2021) Transformers pipeline for offensiveness detection in mexican Spanish social media. In: IberLEF@SEPLN"},{"key":"21521_CR25","unstructured":"Ca\u00f1ete J, Chaperon G, Fuentes R, Ho J-H, Kang H, P\u00e9rez J (2020) Spanish pre-trained bert model and evaluation data. In: PML4DC at ICLR 2020"},{"key":"21521_CR26","unstructured":"Mosbach M, Andriushchenko M, Klakow D (2021) On the Stability of Fine-tuning BERT: misconceptions, explanations, and strong baselines"},{"key":"21521_CR27","unstructured":"Dodge J, Ilharco G, Schwartz R, Farhadi A, Hajishirzi H, Smith N (2020) Fine-tuning pretrained language models: weight initializations, data orders, and early stopping"},{"key":"21521_CR28","doi-asserted-by":"publisher","unstructured":"Anjum, Katarya R (2024) Hatedetector: Multilingual technique for the analysis and detection of online hate speech in social networks. Multimed Tools Appl 83(16):48021\u201348048. https:\/\/doi.org\/10.1007\/s11042-023-16598-x","DOI":"10.1007\/s11042-023-16598-x"},{"issue":"19","key":"21521_CR29","doi-asserted-by":"publisher","first-page":"56763","DOI":"10.1007\/s11042-023-16968-5","volume":"83","author":"ST Luu","year":"2024","unstructured":"Luu ST, Van Nguyen K, Nguyen NL-T (2024) An approach of data augmentation to improve the performance of bertology models for vietnamese hate speech detection. Multimed Tools Appl 83(19):56763\u201356783. https:\/\/doi.org\/10.1007\/s11042-023-16968-5","journal-title":"Multimed Tools Appl"},{"issue":"23","key":"21521_CR30","doi-asserted-by":"publisher","first-page":"36279","DOI":"10.1007\/s11042-023-14850-y","volume":"82","author":"V Dwivedy","year":"2023","unstructured":"Dwivedy V, Roy PK (2023) Deep feature fusion for hate speech detection: a transfer learning approach. Multimed Tools Appl 82(23):36279\u201336301. https:\/\/doi.org\/10.1007\/s11042-023-14850-y","journal-title":"Multimed Tools Appl"},{"issue":"2","key":"21521_CR31","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1109\/TCSS.2022.3157474","volume":"10","author":"S Ghosh","year":"2023","unstructured":"Ghosh S, Ekbal A, Bhattacharyya P, Saha T, Kumar A, Srivastava S (2023) Sehc: A benchmark setup to identify online hate speech in English. IEEE Trans Comput Soc Syst 10(2):760\u2013770. https:\/\/doi.org\/10.1109\/TCSS.2022.3157474","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"21521_CR32","doi-asserted-by":"publisher","unstructured":"Jiang H, He P, Chen W, Liu X, Gao J, Zhao T (2020) SMART: Robust and efficient fine-tuning for pre-trained natural language models through principled regularized optimization. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.197","DOI":"10.18653\/v1\/2020.acl-main.197"},{"key":"21521_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113741","volume":"323","author":"Y Wang","year":"2025","unstructured":"Wang Y, Li J, Zhang H, Zhang J, Wan F, Qiu A, Gao Z (2025) Fedmdd: Multi-deliberation based calibration for federated long-tailed learning. Knowl-Based Syst 323:113741. https:\/\/doi.org\/10.1016\/j.knosys.2025.113741","journal-title":"Knowl-Based Syst"},{"key":"21521_CR34","doi-asserted-by":"publisher","unstructured":"Susnjak T, Hwang P, Reyes N, Barczak ALC, McIntosh T, Ranathunga S (2025) Automating research synthesis with domain-specific large language model fine-tuning. ACM Trans Knowl Discov Data 19(3). https:\/\/doi.org\/10.1145\/3715964","DOI":"10.1145\/3715964"},{"key":"21521_CR35","doi-asserted-by":"crossref","unstructured":"Gururangan S, Marasovi\u0107 A, Swayamdipta S, Lo K, Beltagy I, Downey D, Smith NA (2020) Don\u2019t stop pretraining: adapt language models to domains and tasks","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"21521_CR36","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682","author":"J Lee","year":"2019","unstructured":"Lee J, Yoon W, Kim S, Kim D, Kim S, So CH, Kang J (2019) BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics. https:\/\/doi.org\/10.1093\/bioinformatics\/btz682","journal-title":"Bioinformatics"},{"key":"21521_CR37","doi-asserted-by":"crossref","unstructured":"Conneau A, Khandelwal K, Goyal N, Chaudhary V, Wenzek G, Guzm\u00e1n F, Grave E, Ott M, Zettlemoyer L, Stoyanov V (2020) Unsupervised cross-lingual representation learning at scale","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"21521_CR38","unstructured":"Guo M, Dai Z, Vrandecic D, Al-Rfou R (2020) Wiki-40b: Multilingual language model dataset. In: LREC 2020. http:\/\/www.lrec-conf.org\/proceedings\/lrec2020\/pdf\/2020.lrec-1.296.pdf"},{"key":"21521_CR39","unstructured":"Go A, Bhayani R, Huang L (2009) Twitter sentiment classification using distant supervision. Processing 150"},{"key":"21521_CR40","doi-asserted-by":"crossref","unstructured":"Vu T-T, Phung D, Haffari G (2020) Effective unsupervised domain adaptation with adversarially trained language models","DOI":"10.18653\/v1\/2020.emnlp-main.497"},{"key":"21521_CR41","unstructured":"Goodfellow IJ, Bengio Y, Courville A (2016) Deep learning. MIT Press, Cambridge, MA, USA. http:\/\/www.deeplearningbook.org"},{"key":"21521_CR42","unstructured":"Goodfellow IJ, Shlens J, Szegedy C (2015) Explaining and harnessing adversarial examples"},{"key":"21521_CR43","doi-asserted-by":"publisher","unstructured":"Miyato T, Maeda S-i, Koyama M, Ishii S (2017) Virtual adversarial training: A regularization method for supervised and semi-supervised learning. https:\/\/doi.org\/10.48550\/ARXIV.1704.03976.","DOI":"10.48550\/ARXIV.1704.03976."},{"key":"21521_CR44","doi-asserted-by":"publisher","unstructured":"Zhang H, Yu Y, Jiao J, Xing EP, Ghaoui LE, Jordan MI (2019) Theoretically principled trade-off between robustness and accuracy. https:\/\/doi.org\/10.48550\/ARXIV.1901.08573","DOI":"10.48550\/ARXIV.1901.08573"},{"key":"21521_CR45","doi-asserted-by":"crossref","unstructured":"P\u00e9rez JM, Furman DA, Alemany LA, Luque F (2021) Robertuito: a pre-trained language model for social media text in Spanish. arXiv:2111.09453","DOI":"10.63317\/4v9eufgmyo6q"},{"key":"21521_CR46","doi-asserted-by":"publisher","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) RoBERTa: A robustly optimized BERT pretraining approach. https:\/\/doi.org\/10.48550\/ARXIV.1907.11692","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"21521_CR47","unstructured":"Salazar J, Liang D, Nguyen TQ, Kirchhoff K (2019) Pseudolikelihood reranking with masked language models. arXiv:1910.14659"},{"key":"21521_CR48","doi-asserted-by":"publisher","unstructured":"Strubell E, Ganesh A, McCallum A (2019) Energy and policy considerations for deep learning in NLP. https:\/\/doi.org\/10.48550\/ARXIV.1906.02243","DOI":"10.48550\/ARXIV.1906.02243"},{"issue":"140","key":"21521_CR49","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21(140):1\u201367","journal-title":"J Mach Learn Res"},{"key":"21521_CR50","doi-asserted-by":"crossref","unstructured":"Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L (2019) Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461","DOI":"10.18653\/v1\/2020.acl-main.703"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21521-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-026-21521-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21521-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T21:15:53Z","timestamp":1781644553000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-026-21521-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,31]]},"references-count":50,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["21521"],"URL":"https:\/\/doi.org\/10.1007\/s11042-026-21521-1","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,31]]},"assertion":[{"value":"7 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 January 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This manuscript is the author\u2019s original work and has not been published or submitted simultaneously elsewhere. All authors have reviewed the manuscript and agree to its submission.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"On behalf of all authors, the corresponding author declares that there is no conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The authors have no competing interests relevant to the content of this article.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"This study did not involve human or animal subjects; therefore, ethical approval and informed consent were not applicable. We only used public data and did not contact social media users.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Not applicable.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"Not applicable.","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Publish"}}],"article-number":"323"}}