{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T23:54:19Z","timestamp":1781740459107,"version":"3.54.5"},"reference-count":108,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007957","name":"Chongqing Municipal Education Commission","doi-asserted-by":"publisher","award":["24SKGHIP2"],"award-info":[{"award-number":["24SKGHIP2"]}],"id":[{"id":"10.13039\/501100007957","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.eswa.2026.132507","type":"journal-article","created":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T15:25:20Z","timestamp":1776525920000},"page":"132507","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A survey of multimodal hate meme detection"],"prefix":"10.1016","volume":"323","author":[{"given":"Chengjuan","family":"Ren","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongwon","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7321-0867","authenticated-orcid":false,"given":"Ming","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0226-4839","authenticated-orcid":false,"given":"Yi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9262-4513","authenticated-orcid":false,"given":"Yuejia","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132507_b0005","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., & Anadkat, S. (2023). Gpt-4 technical report. arXiv preprint arXiv:2303.08774."},{"key":"10.1016\/j.eswa.2026.132507_b0010","series-title":"Proceedings of the ACM Web Conference 2023","first-page":"3734","article-title":"HateProof: Are hateful meme detection systems really robust? Association for computing machinery","author":"Aggarwal","year":"2023"},{"key":"10.1016\/j.eswa.2026.132507_b0015","first-page":"104","article-title":"Text or image? what is more Important in Cross-Domain Generalization Capabilities of Hate Meme Detection Models?","volume":"2024","author":"Aggarwal","year":"2024","journal-title":"Association for Computational Linguistics, Findings of the Association for Computational Linguistics: EACL"},{"key":"10.1016\/j.eswa.2026.132507_b0020","doi-asserted-by":"crossref","unstructured":"AlDahoul, N., & Zaki, Y. (2025). Detecting hope, hate, and emotion in Arabic textual speech and multi-modal memes using large language models. arXiv preprint arXiv:2508.15810.","DOI":"10.18653\/v1\/2025.arabicnlp-sharedtasks.76"},{"key":"10.1016\/j.eswa.2026.132507_b0025","doi-asserted-by":"crossref","first-page":"22359","DOI":"10.1109\/ACCESS.2024.3361322","article-title":"Multimodal Hate Speech Detection in Memes using Contrastive Language-image Pre-Training","volume":"12","author":"Arya","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.132507_b0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.is.2024.102378","article-title":"An inter-modal attention-based deep learning framework using unified modality for multimodal fake news, hate speech and offensive language detection","volume":"123","author":"Ayetiran","year":"2024","journal-title":"Information Systems"},{"key":"10.1016\/j.eswa.2026.132507_b0035","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal Machine Learning: A Survey and Taxonomy","volume":"41","author":"Baltru\u0161aitis","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.132507_b0040","series-title":"2024 L Latin American Computer Conference (CLEI)","first-page":"1","article-title":"Beyond Words: A Preliminary Study for Multimodal Hate Speech Detection","author":"Barcel\u00f3","year":"2024"},{"key":"10.1016\/j.eswa.2026.132507_b0045","article-title":"Amharic Language Hate Speech Detection System from Facebook Memes using Deep Learning System","author":"Belete","year":"2023","journal-title":"SSRN Electronic Journal"},{"key":"10.1016\/j.eswa.2026.132507_b0050","doi-asserted-by":"crossref","unstructured":"Bhowmick, R. S., Ganguli, I., Paul, J., & Sil, J. (2021). A Multimodal Deep Framework for Derogatory Social Media Post Identification of a Recognized Person. ACM Trans. Asian Low-Resour. Lang. Inf. Process., 21, Article 2.","DOI":"10.1145\/3447651"},{"key":"10.1016\/j.eswa.2026.132507_b0055","series-title":"In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"9714","article-title":"Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision\u2013Language Models","author":"Bui","year":"2025"},{"key":"10.1016\/j.eswa.2026.132507_b0060","doi-asserted-by":"crossref","unstructured":"Cao, R., Lee, R. K.-W., Chong, W.-H., & Jiang, J. (2023). Prompting for Multimodal Hateful Meme Classification. arXiv preprint arXiv:2302.04156.","DOI":"10.18653\/v1\/2022.emnlp-main.22"},{"key":"10.1016\/j.eswa.2026.132507_b0065","series-title":"Semiotics: The Basics","author":"Chandler","year":"2004"},{"key":"10.1016\/j.eswa.2026.132507_b0070","doi-asserted-by":"crossref","unstructured":"Chen, Y., & Pan, F. (2022). Multimodal Detection of Hateful Messages Using Visual-Linguistic Pre-Trained Deep Learning Models.","DOI":"10.21203\/rs.3.rs-1414253\/v1"},{"key":"10.1016\/j.eswa.2026.132507_b0080","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106991","article-title":"Multimodal hate speech detection via multi-scale visual kernels and knowledge distillation architecture","volume":"126","author":"Chhabra","year":"2023","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.132507_b0085","unstructured":"Chhabra, A., & Vishwakarma, D. K. (2024). Mhs-stma: Multimodal hate speech detection via scalable transformer-based multilevel attention framework. arXiv preprint arXiv:2409.05136."},{"key":"10.1016\/j.eswa.2026.132507_b0090","series-title":"Discourse in late Modernity, Rethinking critical Discourse Analysis","author":"Chouliaraki","year":"1999"},{"key":"10.1016\/j.eswa.2026.132507_b0095","doi-asserted-by":"crossref","unstructured":"Cohen, E., Levy, J., & Roy, J. (2024). An Integrated Multimodal System for Identifying Offensive Memes.","DOI":"10.20944\/preprints202411.1131.v1"},{"key":"10.1016\/j.eswa.2026.132507_b0100","article-title":"Understanding the generalizability of hateful memes detection models against covid-19-related hateful memes","author":"Cuo","year":"2022","journal-title":"International Conference on Machine Learning and"},{"key":"10.1016\/j.eswa.2026.132507_b0105","series-title":"The selfish gene","author":"Dawkins","year":"2006"},{"key":"10.1016\/j.eswa.2026.132507_b0110","series-title":"In Proceedings of the 2021 International Conference on Multimodal Interaction","first-page":"723","article-title":"An Interpretable Approach to Hateful Meme Detection. Association for Computing Machinery","author":"Deshpande","year":"2021"},{"key":"10.1016\/j.eswa.2026.132507_b0115","unstructured":"Devarapalli, L. T. (2024). Multimodal hateful meme classification using Vision Transformer and BERT: California State University, Sacramento."},{"key":"10.1016\/j.eswa.2026.132507_b0120","first-page":"533","article-title":"SemEval-2022 Task 5: Multimedia Automatic Misogyny Identification","author":"Fersini","year":"2022","journal-title":"Association for Computational Linguistics."},{"key":"10.1016\/j.eswa.2026.132507_b0125","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121115","article-title":"Improving hate speech detection using Cross-Lingual Learning","volume":"235","author":"Firmino","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132507_b0130","article-title":"DIMEMEX-2024: CyT at DIMEMEX: Leveraging Data Augmentation for the Detection of Hate Speech in Memes","author":"Garc\u00eda-Hidalgo","year":"2024","journal-title":"IberLEF@SEPLN"},{"key":"10.1016\/j.eswa.2026.132507_b0135","series-title":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","first-page":"1459","article-title":"Exploring Hate Speech Detection in Multimodal Publications","author":"Gomez","year":"2020"},{"key":"10.1016\/j.eswa.2026.132507_b0140","series-title":"Detecting Linguistic Indicators for Stereotype Assessment with Large Language Models. Association for Computing Machinery","first-page":"2796","author":"G\u00f6rge","year":"2025"},{"key":"10.1016\/j.eswa.2026.132507_b0145","series-title":"Event Analytics across Languages and Communities","first-page":"71","article-title":"Processing multimodal information: Challenges and solutions for multimodal sentiment analysis and hate speech detection","author":"Hakimov","year":"2024"},{"key":"10.1016\/j.eswa.2026.132507_b0150","doi-asserted-by":"crossref","unstructured":"Hamza, A., Javed, A. R., Iqbal, F., Yasin, A., Srivastava, G., Po\u0142ap, D., Gadekallu, T. R., & Jalil, Z. (2024). Multimodal Religiously Hateful Social Media Memes Classification Based on Textual and Image Data. ACM Trans. Asian Low-Resour. Lang. Inf. Process., 23, Article 114.","DOI":"10.1145\/3623396"},{"key":"10.1016\/j.eswa.2026.132507_b0155","doi-asserted-by":"crossref","unstructured":"Hashim, A., Coleman, N., & Roy, J. (2024). Toxic Memes Recognition Through with Multimodal Bidirectional Cross-Attention. Preprints.org, 2024111071.","DOI":"10.20944\/preprints202411.1071.v1"},{"key":"10.1016\/j.eswa.2026.132507_b0160","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125843","article-title":"Self-supervised hate speech detection in norwegian texts with lexical and semantic augmentations","volume":"264","author":"Hashmi","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132507_b0165","doi-asserted-by":"crossref","unstructured":"Haslam, N. (2006). Dehumanization: An Integrative Review. Personality and social psychology review : an official journal of the Society for Personality and Social Psychology, Inc, 10, 252-264.","DOI":"10.1207\/s15327957pspr1003_4"},{"key":"10.1016\/j.eswa.2026.132507_b0170","doi-asserted-by":"crossref","unstructured":"Hee, M. S., Chong, W.-H., & Lee, R. K.-W. (2023). Decoding the Underlying Meaning of Multimodal Hateful Memes. arXiv preprint arXiv:2305.17678.","DOI":"10.24963\/ijcai.2023\/665"},{"key":"10.1016\/j.eswa.2026.132507_b0175","doi-asserted-by":"crossref","unstructured":"Hermida, P. C. d. Q., & Santos, E. M. d. (2023). Detecting hate speech in memes: a review. Artificial Intelligence Review, 56, 12833-12851.","DOI":"10.1007\/s10462-023-10459-7"},{"key":"10.1016\/j.eswa.2026.132507_b0180","series-title":"Social semiotics","author":"Hodge","year":"1988"},{"key":"10.1016\/j.eswa.2026.132507_b0185","series-title":"In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"8347","article-title":"Deciphering Hate: Identifying Hateful Memes and their Targets. Association for Computational Linguistics","author":"Hossain","year":"2024"},{"key":"10.1016\/j.eswa.2026.132507_b0190","first-page":"7321","article-title":"Evolver: Chain-of-Evolution Prompting to boost Large Multimodal Models for Hateful Meme Detection","author":"Huang","year":"2025","journal-title":"Association for Computational Linguistics."},{"key":"10.1016\/j.eswa.2026.132507_b0195","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.129906","article-title":"Knowledge-enhanced chinese multimodal hate speech detection","volume":"299","author":"Huang","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132507_b0200","unstructured":"Islam, S. M. J., Mustakim, S., Ahmmed, S., Sayeedi, M., Khandoker, S., Dhrubo, S., & Hossain, N. (2024). MIMIC: Multimodal Islamophobic Meme Identification and Classification. arXiv preprint arXiv:2412.00681."},{"key":"10.1016\/j.eswa.2026.132507_b0205","series-title":"Department of Computer Science and Engineering (CSE)","article-title":"Hate Speech Detection from Multimodal Memes using Vision-Language Transformer Models","author":"Ivan","year":"2024"},{"key":"10.1016\/j.eswa.2026.132507_b0210","first-page":"335","article-title":"Overview of DIMEMEX at iberlef 2024: Detection of inappropriate memes from Mexico","volume":"73","author":"Jarqu\u00edn-V\u00e1squez","year":"2024","journal-title":"Procesamiento del Lenguaje Natural"},{"key":"10.1016\/j.eswa.2026.132507_b0215","unstructured":"Jennifer, C., Tahmasbi, F., Blackburn, J., Stringhini, G., Zannettou, S., & De Cristofaro, E. (2022). Feels Bad Man: Dissecting Automated Hateful Meme Detection Through the Lens of Facebook's Challenge. arXiv preprint arXiv:2202.08492."},{"key":"10.1016\/j.eswa.2026.132507_b0220","volume":"(Vol. 1):","author":"Jewitt","year":"2009"},{"key":"10.1016\/j.eswa.2026.132507_b0225","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.120186","article-title":"A framework for co-evolutionary algorithm using Q-learning with meme","volume":"225","author":"Jiao","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132507_b0230","unstructured":"Jin, W., & Wilhelm, L. (2022). The Hateful Memes Challenge Next Move. arXiv preprint arXiv:2212.06655."},{"key":"10.1016\/j.eswa.2026.132507_b0235","series-title":"In Proceedings of The 32nd Irish Conference on Artificial Intelligence and Cognitive Science","first-page":"266","article-title":"The Impact of CLIP Encoders and CNN Architectures on Model Efficiency: A Case Study on Hate Speech Detection. CEUR-WS.org","author":"K\u00e4lin","year":"2024"},{"key":"10.1016\/j.eswa.2026.132507_b0240","doi-asserted-by":"crossref","DOI":"10.1016\/j.nlp.2025.100133","article-title":"A transformer based multi task learning approach to multimodal hate speech detection","volume":"11","author":"Kapil","year":"2025","journal-title":"Natural Language Processing Journal"},{"key":"10.1016\/j.eswa.2026.132507_b0245","doi-asserted-by":"crossref","unstructured":"Karim, M. R., Dey, S. K., Islam, T., Shajalal, M., & Chakravarthi, B. R. (2023). Multimodal Hate Speech Detection from Bengali Memes and Texts. Springer International Publishing. Speech and Language Technologies for Low-Resource Languages, pp. 293-308.","DOI":"10.1007\/978-3-031-33231-9_21"},{"key":"10.1016\/j.eswa.2026.132507_b0250","first-page":"2611","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","volume":"33","author":"Kiela","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"10.1016\/j.eswa.2026.132507_b0255","series-title":"Image-based Content. Companion Proceedings of the ACM on Web Conference 2025","first-page":"2014","article-title":"Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs","author":"Koushik","year":"2025"},{"key":"10.1016\/j.eswa.2026.132507_b0260","series-title":"Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI)","first-page":"171","article-title":"Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features","author":"Kumar","year":"2022"},{"key":"10.1016\/j.eswa.2026.132507_b0265","series-title":"Hateful meme classification of Indian political memes. Computational Methods in Science and Technology","first-page":"549","author":"Kumar","year":"2024"},{"key":"10.1016\/j.eswa.2026.132507_b0270","series-title":"Metaphors we live by","author":"Lakoff","year":"2024"},{"key":"10.1016\/j.eswa.2026.132507_b0275","series-title":"Introducing social semiotics","author":"Leeuwen","year":"2005"},{"key":"10.1016\/j.eswa.2026.132507_b0280","unstructured":"Li, L., Yatskar, M., Yin, D., Hsieh, C., & Chang, K. (2019). A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557, 5."},{"key":"10.1016\/j.eswa.2026.132507_b0285","series-title":"In Proceedings of the 57th Hawaii International Conference on System Sciences","first-page":"7215","article-title":"Towards resource inequities in catching the \u201cdark side\u201d of social media: A hateful meme classification framework for low-resource scenarios. HICSS","author":"Li","year":"2024"},{"key":"10.1016\/j.eswa.2026.132507_b0290","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"10.1016\/j.eswa.2026.132507_b0295","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121031","article-title":"A cross-lingual transfer learning method for online COVID-19-related hate speech detection","volume":"234","author":"Liu","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132507_b0305","series-title":"How to do critical discourse analysis: A multimodal introduction","author":"Machin","year":"2023"},{"key":"10.1016\/j.eswa.2026.132507_b0300","doi-asserted-by":"crossref","first-page":"4525","DOI":"10.3390\/math10234525","article-title":"Hateful memes detection based on multi-task learning","volume":"10","author":"Ma","year":"2022","journal-title":"Mathematics"},{"key":"10.1016\/j.eswa.2026.132507_b0310","doi-asserted-by":"crossref","first-page":"189","DOI":"10.2307\/416612","article-title":"Critical Discourse Analysis: The critical Analysis of Language","volume":"73","author":"Mair","year":"1997","journal-title":"Language"},{"key":"10.1016\/j.eswa.2026.132507_b0315","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1007\/s11227-024-06602-y","article-title":"Research on multimodal hate speech detection based on self-attention mechanism feature fusion: J. Mao et al","volume":"81","author":"Mao","year":"2025","journal-title":"The Journal of Supercomputing"},{"key":"10.1016\/j.eswa.2026.132507_b0320","doi-asserted-by":"crossref","unstructured":"Maqbool, F., & Fersini, E. (2024). Multimodal Hate Speech Detection in Memes from Mexico using BLIP. IEEE Access (Volume: 12). In IberLEF@SEPLN, pp. 22359 - 22375.","DOI":"10.1109\/ACCESS.2024.3361322"},{"key":"10.1016\/j.eswa.2026.132507_b0325","series-title":"The Hateful Memes Challenge: Detecting Hate Speech in Multi-Modal Memes","author":"Marutyan","year":"2024"},{"key":"10.1016\/j.eswa.2026.132507_b0330","unstructured":"Mei, J., Chen, J., Yang, G., Lin, W., & Byrne, B. (2025). Improved Fine-Tuning of Large Multimodal Models for Hateful Meme Detection. arXiv preprint arXiv: 2502.13061."},{"key":"10.1016\/j.eswa.2026.132507_b0335","series-title":"DANKMEMES @ EVALITA 2020: The Memeing of Life: Memes, Multimodality and Politics. Proceedings of the Seventh Evaluation Campaign of Natural Language Processing and Speech Tools for Italian Final Workshop (EVALITA, 2020)","author":"Miliani","year":"2020"},{"key":"10.1016\/j.eswa.2026.132507_b0340","doi-asserted-by":"crossref","unstructured":"Miyanishi, Y., & Le Nguyen, M. (2024). Causal Intersectionality and Dual Form of Gradient Descent for Multimodal Analysis: A Case Study on Hateful Memes. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 2901-2916.","DOI":"10.63317\/46vd9wubqojf"},{"key":"10.1016\/j.eswa.2026.132507_b0345","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/0010-0277(96)00711-1","article-title":"On metaphoric representation","volume":"60","author":"Murphy","year":"1996","journal-title":"Cognition"},{"key":"10.1016\/j.eswa.2026.132507_b0350","unstructured":"Nandi, P., Sharma, S., & Chakraborty, T. (2024). SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes. arXiv preprint arXiv:2412.20541."},{"key":"10.1016\/j.eswa.2026.132507_b0355","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2025.3613694","article-title":"Contrastive and Attention-based Multimodal Fusion: Detecting negative Memes through Diverse Fusion strategies. IEEe","author":"Narendiran","year":"2025","journal-title":"Access"},{"key":"10.1016\/j.eswa.2026.132507_b0360","volume":"27","author":"Nguyen","year":"2025","journal-title":"Journal of Medical Internet Research"},{"key":"10.1016\/j.eswa.2026.132507_b0365","series-title":"Multimodal Hate Speech Detection in Memes","author":"Oriol S\u00e0bat","year":"2019"},{"key":"10.1016\/j.eswa.2026.132507_b0370","article-title":"The PRISMA 2020 statement: An updated guideline for reporting systematic reviews","volume":"372","author":"Page","year":"2021","journal-title":"BMJ"},{"key":"10.1016\/j.eswa.2026.132507_b0375","doi-asserted-by":"crossref","first-page":"4505","DOI":"10.1007\/s41870-024-02113-4","article-title":"Differently processed modality and appropriate model selection lead to richer representation of the multimodal input","volume":"16","author":"Panda","year":"2024","journal-title":"International Journal of Information Technology"},{"key":"10.1016\/j.eswa.2026.132507_b0380","article-title":"UCM's Participation to the 2024 DIMEMEX Task: Automatic Detection of Inappropriate Memes in Mexico","author":"Parveen","year":"2024","journal-title":"IberLEF@SEPLN"},{"key":"10.1016\/j.eswa.2026.132507_b0385","unstructured":"Peirce, C. S. (1931\u20131958). Collected Papers of Charles Sanders Peirce (Vol. 8). Cambridge, MA: Harvard University Press."},{"key":"10.1016\/j.eswa.2026.132507_b0390","series-title":"The ambivalent internet: Mischief, oddity, and antagonism online","author":"Phillips","year":"2018"},{"key":"10.1016\/j.eswa.2026.132507_b0395","doi-asserted-by":"crossref","DOI":"10.1016\/j.dcm.2024.100755","article-title":"Multimodal computation or interpretation? Automatic vs. critical understanding of text-image relations in racist memes in English","volume":"57","author":"Polli","year":"2024","journal-title":"Discourse, Context & Media"},{"key":"10.1016\/j.eswa.2026.132507_b0400","doi-asserted-by":"crossref","first-page":"13020","DOI":"10.1038\/s41598-025-94069-z","article-title":"A comprehensive framework for multi-modal hate speech detection in social media using deep learning","volume":"15","author":"Prabhu","year":"2025","journal-title":"Scientific Reports"},{"key":"10.1016\/j.eswa.2026.132507_b0405","first-page":"2783","article-title":"Detecting Harmful Memes and their Targets","author":"Pramanick","year":"2021","journal-title":"Association for Computational Linguistics."},{"key":"10.1016\/j.eswa.2026.132507_b0410","series-title":"Proceedings of the 2023 ACM SIGSAC conference on computer and communications security","first-page":"3403","article-title":"Unsafe diffusion: On the generation of unsafe images and hateful memes from text-to-image models","author":"Qu","year":"2023"},{"key":"10.1016\/j.eswa.2026.132507_b0415","series-title":"In Proceedings of the 38th International Conference on Machine Learning","first-page":"8748","article-title":"Learning Transferable Visual Models from Natural Language Supervision. PMLR","author":"Radford","year":"2021"},{"key":"10.1016\/j.eswa.2026.132507_b0420","unstructured":"Rajput, K., Kapoor, R., Rai, K., & Kaur, P. (2022). Hate Me Not: Detecting Hate Inducing Memes in Code Switched Languages. arXiv preprint arXiv:2204.11356."},{"key":"10.1016\/j.eswa.2026.132507_b0425","series-title":"Proceedings of the International AAAI Conference on Web and Social Media","first-page":"1669","article-title":"Exploring the Limits of Zero Shot Vision Language Models for Hate Meme Detection: The Vulnerabilities and their Interpretations","author":"Rizwan","year":"2025"},{"key":"10.1016\/j.eswa.2026.132507_b0430","doi-asserted-by":"crossref","first-page":"e2801","DOI":"10.7717\/peerj-cs.2801","article-title":"Multimodal hate speech detection: A novel deep learning framework for multilingual text and images","volume":"11","author":"Saddozai","year":"2025","journal-title":"PeerJ Computer Science"},{"key":"10.1016\/j.eswa.2026.132507_b0435","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1007\/s42979-021-01007-7","article-title":"Explorative Application of Fusion Techniques for Multimodal Hate Speech Detection","volume":"3","author":"Sai","year":"2022","journal-title":"SN Computer Science"},{"key":"10.1016\/j.eswa.2026.132507_b0440","unstructured":"Sandulescu, V. (2020). Detecting Hateful Memes Using a Multimodal Deep Ensemble. arXiv preprint arXiv:2012.13235."},{"key":"10.1016\/j.eswa.2026.132507_b0445","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"17320","article-title":"MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classification","author":"Shah","year":"2024"},{"key":"10.1016\/j.eswa.2026.132507_b0450","doi-asserted-by":"crossref","unstructured":"Sharma, C., Bhageria, D., Scott, W., PYKL, S., Das, A., Chakraborty, T., Pulabaigari, V., & Gamb\u00e4ck, B. (2020). SemEval-2020 Task 8: Memotion Analysis- the Visuo-Lingual Metaphor! International Committee for Computational Linguistics. pp. 759-773.","DOI":"10.18653\/v1\/2020.semeval-1.99"},{"key":"10.1016\/j.eswa.2026.132507_b0455","doi-asserted-by":"crossref","unstructured":"Su, X., Li, Y., Inkpen, D., & Japkowicz, N. (2024). HateSieve: A Contrastive Learning Framework for Detecting and Segmenting Hateful Content in Multimodal Memes. arXiv preprint arXiv:2408.05794.","DOI":"10.18653\/v1\/2025.findings-naacl.289"},{"key":"10.1016\/j.eswa.2026.132507_b0460","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1080\/15551393.2025.2455495","article-title":"From Internet Meme to the mainstream: Using Computer Vision to Track \u201cPepe the Frog\u201d across News Platforms","volume":"32","author":"Sun","year":"2025","journal-title":"Visual Communication Quarterly"},{"key":"10.1016\/j.eswa.2026.132507_b0465","first-page":"7","article-title":"A Dataset for Troll Classification of TamilMemes","author":"Suryawanshi","year":"2020","journal-title":"European Language Resources Association (ELRA)."},{"key":"10.1016\/j.eswa.2026.132507_b0470","doi-asserted-by":"crossref","DOI":"10.1016\/j.mlwa.2025.100647","article-title":"Effective multimodal hate speech detection on Facebook hate memes dataset using incremental PCA, SMOTE, and adversarial learning","volume":"20","author":"Tchokote","year":"2025","journal-title":"Machine Learning with Applications"},{"key":"10.1016\/j.eswa.2026.132507_b0475","series-title":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","first-page":"202","article-title":"Improving Multimodal Hateful Meme Detection Exploiting LMM-Generated Knowledge","author":"Tzelepi","year":"2025"},{"key":"10.1016\/j.eswa.2026.132507_b0480","doi-asserted-by":"crossref","unstructured":"Valle-Cano, G. d., Quijano-S\u00e1nchez, L., Liberatore, F., & G\u00f3mez, J. (2023). SocialHaterBERT: A dichotomous approach for automatically detecting hate speech on Twitter through textual analysis and user profiles. Expert Systems with Applications, 216, 119446.","DOI":"10.1016\/j.eswa.2022.119446"},{"key":"10.1016\/j.eswa.2026.132507_b0485","volume":"ArXiv","author":"Van","year":"2023","journal-title":"Detecting and Correcting Hate Speech in Multimodal Memes with Large Visual Language Model."},{"key":"10.1016\/j.eswa.2026.132507_b0490","unstructured":"Velioglu, R., & Rose, J. (2020). Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge. arXiv preprint arXiv:2012.12975."},{"key":"10.1016\/j.eswa.2026.132507_b0495","series-title":"Italian Association for Computational Linguistics. Proceedings of the Seventh Evaluation Campaign of Natural Language Processing and Speech Tools for Italian","article-title":"UPB @ DANKMEMES: Italian Memes Analysis - Employing Visual Models and Graph Convolutional Networks for Meme Identification and Hate Speech Detection","author":"Vlad","year":"2020"},{"key":"10.1016\/j.eswa.2026.132507_b0505","unstructured":"Wang, Y., & Markov, I. (2024). CLTL at DIMEMEX shared task: Fine-grained detection of hate speech in memes. Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2024), colocated with the Conference of the Spanish Society for Natural Language Processing (SEPLN 2024)."},{"key":"10.1016\/j.eswa.2026.132507_b0500","doi-asserted-by":"crossref","first-page":"9545","DOI":"10.1109\/TCSVT.2025.3550900","article-title":"Few-Shot In-Context Learning for Implicit Semantic Multimodal Content Detection and Interpretation","volume":"35","author":"Wang","year":"2025","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"13","key":"10.1016\/j.eswa.2026.132507_b0510","doi-asserted-by":"crossref","first-page":"2780","DOI":"10.3390\/electronics13142780","article-title":"Multimodal Hateful Meme Classification based on transfer Learning and a Cross-Mask Mechanism","volume":"2024","author":"Wu","year":"2024","journal-title":"Electronics"},{"key":"10.1016\/j.eswa.2026.132507_b0515","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103772","article-title":"Fuser: An enhanced multimodal fusion framework with congruent reinforced perceptron for hateful memes detection","volume":"61","author":"Wu","year":"2024","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.eswa.2026.132507_b0520","series-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","first-page":"1103","article-title":"Tensor Fusion Network for Multimodal sentiment Analysis","author":"Zadeh","year":"2017"},{"key":"10.1016\/j.eswa.2026.132507_b0525","doi-asserted-by":"crossref","first-page":"4749","DOI":"10.1109\/JIOT.2020.3028574","article-title":"Integrated Multiple Kernel Learning for Device-Free Localization in Cluttered Environments using Spatiotemporal Information","volume":"8","author":"Zhang","year":"2021","journal-title":"IEEE Internet of Things Journal"},{"key":"10.1016\/j.eswa.2026.132507_b0530","doi-asserted-by":"crossref","first-page":"8528","DOI":"10.1109\/TII.2022.3218666","article-title":"Online Spatiotemporal Modeling for Robust and Lightweight Device-Free Localization in Nonstationary Environments","volume":"19","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.eswa.2026.132507_b0535","unstructured":"Zhao, B., Zhang, A., Watson, B., Kearney, G., & Dale, I. (2023). A Review of Vision-Language Models and their Performance on the Hateful Memes Challenge. arXiv preprint arXiv:2305.06159."},{"key":"10.1016\/j.eswa.2026.132507_b0540","unstructured":"Zheng, X., Liao, C., Fu, Y., Lei, K., Lyu, Y., Jiang, L., Ren, B., Chen, J., Wang, J., Li, C., Zhang, L., Paudel, D. P., Huang, X., Jiang, Y.-G., Sebe, N., Tao, D., Gool, L. v., & Hu, X. (2025). MLLMs are Deeply Affected by Modality Bias. arXiv preprint arXiv:2505.18657."},{"key":"10.1016\/j.eswa.2026.132507_b0545","unstructured":"Zhu, R. (2020). Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solution. arXiv preprint arXiv:2012.08290."}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095741742601420X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095741742601420X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T23:30:20Z","timestamp":1781739020000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095741742601420X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":108,"alternative-id":["S095741742601420X"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132507","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A survey of multimodal hate meme detection","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132507","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"132507"}}