{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:08:25Z","timestamp":1767262105827,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031785375"},{"type":"electronic","value":"9783031785382"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78538-2_29","type":"book-chapter","created":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T07:28:45Z","timestamp":1737703725000},"page":"331-342","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Hate Speech Classification in\u00a0Text-Embedded Images: Integrating Ontology, Contextual Semantics, and\u00a0Vision-Language Representations"],"prefix":"10.1007","author":[{"given":"Surendrabikram","family":"Thapa","sequence":"first","affiliation":[]},{"given":"Surabhi","family":"Adhikari","sequence":"additional","affiliation":[]},{"given":"Imran","family":"Razzak","sequence":"additional","affiliation":[]},{"given":"Roy Ka-Wei","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Usman","family":"Naseem","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,25]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Bhandari, A., Shah, S.B., Thapa, S., Naseem, U., Nasim, M.: CrisisHateMM: multimodal analysis of directed and undirected hate speech in text-embedded images from Russia-Ukraine conflict. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1993\u20132002 (2023)","DOI":"10.1109\/CVPRW59228.2023.00193"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Z., Xie, L., Niu, J., Liu, X., Wei, L., Tian, Q.: Visformer: the vision-friendly transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 589\u2013598 (2021)","DOI":"10.1109\/ICCV48922.2021.00063"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Chhabra, A., Vishwakarma, D.K.: A literature survey on multimodal and multilingual automatic hate speech identification. Multimedia Systems, pp. 1\u201328 (2023)","DOI":"10.1007\/s00530-023-01051-8"},{"key":"29_CR4","unstructured":"Eisenstein, J., Ahmed, A., Xing, E.P.: Sparse additive generative models of text. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp. 1041\u20131048 (2011)"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"ElSherief, M., Kulkarni, V., Nguyen, D., Wang, W.Y., Belding, E.: Hate lingo: a target-based linguistic analysis of hate speech in social media. In: Proceedings of the International AAAI Conference on Web and Social Media. vol.\u00a012 (2018)","DOI":"10.1609\/icwsm.v12i1.15041"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Fellbaum, C.: WordNet. In: Theory and applications of ontology: computer applications, pp. 231\u2013243. Springer (2010)","DOI":"10.1007\/978-90-481-8847-5_10"},{"key":"29_CR7","unstructured":"Gong, T., et al.: Multimodal-GPT: A vision and language model for dialogue with humans. arXiv preprint arXiv:2305.04790 (2023)"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"29_CR9","unstructured":"Kenton, J.D., Chang, M.W., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Lee, R.K.W., Cao, R., Fan, Z., Jiang, J., Chong, W.H.: Disentangling hate in online memes. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 5138\u20135147 (2021)","DOI":"10.1145\/3474085.3475625"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Li, Y., Wu, C.Y., Fan, H., Mangalam, K., Xiong, B., Malik, J., Feichtenhofer, C.: MViTv2: improved multiscale vision transformers for classification and detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4804\u20134814 (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Loper, E., Bird, S.: NLTK: The Natural Language Toolkit. arXiv preprint cs\/0205028 (2002)","DOI":"10.3115\/1118108.1118117"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Maheshappa, P., Mathew, B., Saha, P.: Using knowledge graphs to improve hate speech detection. In: Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD), pp. 430\u2013430 (2021)","DOI":"10.1145\/3430984.3431072"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Mekki, A., Zribi, I., Ellouze, M., Belguith, L.H.: Tokenization of Tunisian Arabic: a comparison between three machine learning models. ACM Transactions on Asian and Low-Resource Language Information Processing (2023)","DOI":"10.1145\/3599234"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Montariol, S., Riabi, A., Seddah, D.: Multilingual auxiliary tasks training: bridging the gap between languages for zero-shot transfer of hate speech detection models. In: Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022, pp. 347\u2013363 (2022)","DOI":"10.18653\/v1\/2022.findings-aacl.33"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Naseem, U., Kim, J., Khushi, M., Dunn, A.G.: A multimodal framework for the identification of vaccine critical memes on twitter. In: Proceedings of the 16th ACM International Conference on Web Search and Data Mining, pp. 706\u2013714 (2023)","DOI":"10.1145\/3539597.3570450"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Pramanick, S., Sharma, S., Dimitrov, D., Akhtar, M.S., Nakov, P., Chakraborty, T.: MOMENTA: a multimodal framework for detecting harmful memes and their targets. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 4439\u20134455 (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"key":"29_CR18","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"29_CR19","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)"},{"key":"29_CR20","unstructured":"Santurkar, S., Tsipras, D., Ilyas, A., Madry, A.: How does batch normalization help optimization? Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"29_CR21","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"29_CR22","unstructured":"Wang, W., et\u00a0al.: CogVLM: Visual expert for pretrained language models. arXiv preprint arXiv:2311.03079 (2023)"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Wiegand, M., Ruppenhofer, J., Schmidt, A., Greenberg, C.: Inducing a lexicon of abusive words\u2013a feature-based approach. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 1046\u20131056 (2018)","DOI":"10.18653\/v1\/N18-1095"},{"issue":"3","key":"29_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1361684.1361686","volume":"26","author":"HC Wu","year":"2008","unstructured":"Wu, H.C., Luk, R.W.P., Wong, K.F., Kwok, K.L.: Interpreting TF-IDF term weights as making relevance decisions. ACM Trans. Inf. Syst. (TOIS) 26(3), 1\u201337 (2008)","journal-title":"ACM Trans. Inf. Syst. (TOIS)"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: GroupViT: semantic segmentation emerges from text supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18134\u201318144 (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"29_CR26","doi-asserted-by":"publisher","first-page":"15561","DOI":"10.1109\/ACCESS.2021.3052937","volume":"9","author":"N Zhao","year":"2021","unstructured":"Zhao, N., Gao, H., Wen, X., Li, H.: Combination of convolutional neural network and gated recurrent unit for aspect-based sentiment analysis. IEEE Access 9, 15561\u201315569 (2021)","journal-title":"IEEE Access"}],"container-title":["Lecture Notes in Computer Science","Social Networks Analysis and Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78538-2_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T07:29:10Z","timestamp":1737703750000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78538-2_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031785375","9783031785382"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78538-2_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ASONAM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advances in Social Networks Analysis and Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rende","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"asonam-12024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/asonam.cpsc.ucalgary.ca\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}