{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T12:43:40Z","timestamp":1780577020421,"version":"3.54.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T00:00:00Z","timestamp":1729209600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T00:00:00Z","timestamp":1729209600000},"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":["J Supercomput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11227-024-06602-y","type":"journal-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T16:02:24Z","timestamp":1729267344000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Research on multimodal hate speech detection based on self-attention mechanism feature fusion"],"prefix":"10.1007","volume":"81","author":[{"given":"Junjie","family":"Mao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanxiao","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,18]]},"reference":[{"key":"6602_CR1","doi-asserted-by":"publisher","unstructured":"Gomez R, Gibert J, Gomez L, Karatzas D (2020) Exploring hate speech detection in multimodal publications. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 1470\u20131478. https:\/\/doi.org\/10.1109\/WACV45572.2020.9093414","DOI":"10.1109\/WACV45572.2020.9093414"},{"key":"6602_CR2","unstructured":"Guterres A (2019) United Nations strategy and plan of action on hate speech. United Nations. https:\/\/www.un.org\/en\/hate-speech\/un-strategy-and-plan-of-action-on-hate-speech"},{"key":"6602_CR3","unstructured":"Mora D (2022) New UN study finds that hate speech in Costa Rica grew by 71%. https:\/\/unsdg.un.org\/latest\/stories\/new-un-study-finds-hate-speech-costa-rica-grew-71"},{"key":"6602_CR4","unstructured":"Yadav A, Chandel S, Chatufale S, Bandhakavi A (2023) Lahm: large annotated dataset for multi-domain and multilingual hate speech identification. arXiv preprint arXiv:2304.00913. https:\/\/arxiv.org\/pdf\/2304.00913"},{"key":"6602_CR5","unstructured":"Leite JA, Scarton C, Silva DF (2023) Noisy self-training with data augmentations for offensive and hate speech detection tasks. arXiv preprint arXiv:2307.16609. https:\/\/arxiv.org\/pdf\/2307.16609"},{"key":"6602_CR6","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s11192-020-03737-6","volume":"126","author":"A Tontodimamma","year":"2021","unstructured":"Tontodimamma A, Nissi E, Sarra A, Fontanella L (2021) Thirty years of research into hate speech: topics of interest and their evolution. Scientometrics 126:157\u2013179. https:\/\/doi.org\/10.1007\/s11192-020-03737-6","journal-title":"Scientometrics"},{"key":"6602_CR7","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.ins.2023.01.116","volume":"628","author":"J Wang","year":"2023","unstructured":"Wang J, Wang S, Lin M, Xu Z, Guo W (2023) Learning speaker-independent multimodal representation for sentiment analysis. Inf Sci 628:208\u2013225. https:\/\/doi.org\/10.1016\/j.ins.2023.01.116","journal-title":"Inf Sci"},{"key":"6602_CR8","unstructured":"Capozzi Arthur TE, Mirko L, Valerio B, Fabio P, Sanguinetti M, Cristina B, Marco S (2019) Computational linguistics against hate: hate speech detection and visualization on social media in the \u201cContro L\u2019Odio\u201d project. In: CEUR workshop proceedings, vol 2481. CEUR-WS. https:\/\/iris.unica.it\/bitstream\/11584\/389784\/1\/clic2019_hs-cl.pdf"},{"key":"6602_CR9","doi-asserted-by":"crossref","unstructured":"Basile V, Bosco C, Fersini E, Nozza D, Patti V, Pardo FMR, 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, pp 54\u201363. https:\/\/aclanthology.org\/S19-2007.pdf","DOI":"10.18653\/v1\/S19-2007"},{"key":"6602_CR10","doi-asserted-by":"publisher","unstructured":"Florio K, Basile V, Lai M, Patti V (2019). Leveraging hate speech detection to investigate immigration-related phenomena in Italy. In: 2019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW), pp 1\u20137. IEEE. https:\/\/doi.org\/10.1109\/ACIIW.2019.8925079","DOI":"10.1109\/ACIIW.2019.8925079"},{"issue":"8","key":"6602_CR11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0237861","volume":"15","author":"M Mozafari","year":"2020","unstructured":"Mozafari M, Farahbakhsh R, Crespi N (2020) Hate speech detection and racial bias mitigation in social media based on BERT model. PLoS ONE 15(8):e0237861. https:\/\/doi.org\/10.1371\/journal.pone.0237861","journal-title":"PLoS ONE"},{"issue":"3","key":"6602_CR12","doi-asserted-by":"publisher","first-page":"205630512211047","DOI":"10.1177\/20563051221104749","volume":"8","author":"J Uyheng","year":"2022","unstructured":"Uyheng J, Bellutta D, Carley KM (2022) Bots amplify and redirect hate speech in online discourse about racism during the COVID-19 pandemic. Soc Media Soc 8(3):20563051221104748. https:\/\/doi.org\/10.1177\/20563051221104749","journal-title":"Soc Media Soc"},{"key":"6602_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114120","volume":"166","author":"FM Plaza-del-Arco","year":"2021","unstructured":"Plaza-del-Arco FM, Molina-Gonz\u00e1lez MD, Urena-L\u00f3pez LA, Mart\u00edn-Valdivia MT (2021) Comparing pre-trained language models for Spanish hate speech detection. Expert Syst Appl 166:114120. https:\/\/doi.org\/10.1016\/j.eswa.2020.114120","journal-title":"Expert Syst Appl"},{"issue":"7","key":"6602_CR14","doi-asserted-by":"publisher","first-page":"3629","DOI":"10.1007\/s41870-022-01096-4","volume":"14","author":"S Akuma","year":"2022","unstructured":"Akuma S, Lubem T, Adom IT (2022) Comparing bag of words and TF-IDF with different models for hate speech detection from live tweets. Int J Inf Technol 14(7):3629\u20133635. https:\/\/doi.org\/10.1007\/s41870-022-01096-4","journal-title":"Int J Inf Technol"},{"issue":"6","key":"6602_CR15","doi-asserted-by":"publisher","first-page":"273","DOI":"10.3390\/info13060273","volume":"13","author":"F Alkomah","year":"2022","unstructured":"Alkomah F, Ma X (2022) A literature review of textual hate speech detection methods and datasets. Information 13(6):273. https:\/\/doi.org\/10.3390\/info13060273","journal-title":"Information"},{"issue":"8","key":"6602_CR16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0221152","volume":"14","author":"S MacAvaney","year":"2019","unstructured":"MacAvaney S, Yao HR, Yang E, Russell K, Goharian N, Frieder O (2019) Hate speech detection: challenges and solutions. PLoS ONE 14(8):e0221152. https:\/\/doi.org\/10.1371\/journal.pone.0221152","journal-title":"PLoS ONE"},{"key":"6602_CR17","doi-asserted-by":"publisher","unstructured":"Gamb\u00e4ck B, Sikdar UK (2017). Using convolutional neural networks to classify hate-speech. In: Proceedings of the first workshop on abusive language online, pp 85\u201390. https:\/\/doi.org\/10.18653\/v1\/W17-3013","DOI":"10.18653\/v1\/W17-3013"},{"issue":"23","key":"6602_CR18","doi-asserted-by":"publisher","first-page":"8614","DOI":"10.3390\/app10238614","volume":"10","author":"R Alshalan","year":"2020","unstructured":"Alshalan R, Al-Khalifa H (2020) A deep learning approach for automatic hate speech detection in the Saudi twittersphere. Appl Sci 10(23):8614. https:\/\/doi.org\/10.3390\/app10238614","journal-title":"Appl Sci"},{"key":"6602_CR19","unstructured":"Tan M (2019) Efficientnet: rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946. https:\/\/rxiv.org\/abs\/1905.11946"},{"issue":"2","key":"6602_CR20","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/s42979-021-01007-7","volume":"3","author":"S Sai","year":"2022","unstructured":"Sai S, Srivastava ND, Sharma Y (2022) Explorative application of fusion techniques for multimodal hate speech detection. SN Comput Sci 3(2):122. https:\/\/doi.org\/10.1007\/s42979-021-01007-7","journal-title":"SN Comput Sci"},{"key":"6602_CR21","unstructured":"Liang Yi T, Tuerdi T (2023) Multimodal fake information detection using multi-layer CNN feature fusion and multi-classifier ensemble prediction. Comput Eng Sci https:\/\/kns.cnki.net\/kcms2\/article\/abstract?v=bh5BUr5hMuVOZ89CJ0yy4UtbDD72fKvyRiR9xyB-TIpsal-6RVRdhWdotCyBZqex1qR_gPy_jObrqs1QtO6VbjtMunpifN6MCvW958N07dmaUt_uZpuMk2-b6nA1hOHLZORmUfpsPqkJ2muS9Wqvwlr6wVv63mxWCdJHZg7UM--JuwEdOmiuX-gF3y6X_BmORkSpz1JmBoM=&uniplatform=NZKPT&language=CHS"},{"key":"6602_CR22","doi-asserted-by":"publisher","unstructured":"Yang C, Zhu F, Liu G, Han J, Hu S (2022). Multimodal hate speech detection via cross-domain knowledge transfer. In: Proceedings of the 30th ACM International Conference on Multimedia, pp 4505\u20134514. https:\/\/doi.org\/10.1145\/3503161.3548255","DOI":"10.1145\/3503161.3548255"},{"key":"6602_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106991","volume":"126","author":"A Chhabra","year":"2023","unstructured":"Chhabra A, Vishwakarma DK (2023) Multimodal hate speech detection via multi-scale visual kernels and knowledge distillation architecture. Eng Appl Artif Intell 126:106991. https:\/\/doi.org\/10.1016\/j.engappai.2023.106991","journal-title":"Eng Appl Artif Intell"},{"key":"6602_CR24","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1016\/j.inffus.2021.05.015","volume":"75","author":"W Zheng","year":"2021","unstructured":"Zheng W, Yan L, Gou C, Zhang ZC, Zhang JJ, Hu M, Wang FY (2021) Pay attention to doctor\u2013patient dialogues: multi-modal knowledge graph attention image-text embedding for COVID-19 diagnosis. Inform Fus 75:168\u2013185. https:\/\/doi.org\/10.1016\/j.inffus.2021.05.015","journal-title":"Inform Fus"},{"key":"6602_CR25","doi-asserted-by":"publisher","unstructured":"Sangwan S, Akhtar MS, Behera P, Ekbal A (2020). I didn\u2019t mean what I wrote! exploring multimodality for sarcasm detection. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp 1\u20138. IEEE. https:\/\/doi.org\/10.1109\/IJCNN48605.2020.9206905","DOI":"10.1109\/IJCNN48605.2020.9206905"},{"key":"6602_CR26","unstructured":"Liu Y (2019) Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692. https:\/\/arxiv.org\/abs\/1907.11692"},{"key":"6602_CR27","doi-asserted-by":"publisher","unstructured":"Yu J, Lin Z, Yang J, Shen X, Lu X, Huang TS (2019) Free-form image inpainting with gated convolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 4471\u20134480. https:\/\/doi.org\/10.1109\/ICCV.2019.00457","DOI":"10.1109\/ICCV.2019.00457"},{"key":"6602_CR28","unstructured":"Zhu R (2020) Enhance multimodal transformer with external label and in-domain pretrain: hateful meme challenge winning solution. arXiv preprint arXiv:2012.08290. https:\/\/arxiv.org\/abs\/2012.08290"},{"key":"6602_CR29","doi-asserted-by":"publisher","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 10012\u201310022). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"6602_CR30","first-page":"2611","volume":"33","author":"D Kiela","year":"2020","unstructured":"Kiela D, Firooz H, Mohan A, Goswami V, Singh A, Ringshia P, Testuggine D (2020) The hateful memes challenge: detecting hate speech in multimodal memes. Adv Neural Inform Process Syst 33:2611\u20132624","journal-title":"Adv Neural Inform Process Syst"},{"issue":"3","key":"6602_CR31","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1007\/s00530-023-01051-8","volume":"29","author":"A Chhabra","year":"2023","unstructured":"Chhabra A, Vishwakarma DK (2023) A literature survey on multimodal and multilingual automatic hate speech identification. Multim Syst 29(3):1203\u20131230. https:\/\/doi.org\/10.1007\/s00530-023-01051-8","journal-title":"Multim Syst"},{"key":"6602_CR32","doi-asserted-by":"publisher","unstructured":"Lee RKW, Cao R, Fan Z, Jiang J, Chong WH (2021). Disentangling hate in online memes. In: Proceedings of the 29th ACM International Conference on Multimedia, pp 5138\u20135147. https:\/\/doi.org\/10.1145\/3474085.347562","DOI":"10.1145\/3474085.347562"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06602-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06602-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06602-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T16:07:13Z","timestamp":1729267633000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06602-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,18]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6602"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06602-y","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,18]]},"assertion":[{"value":"7 October 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 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 declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"28"}}