{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T09:17:20Z","timestamp":1783156640328,"version":"3.54.6"},"reference-count":42,"publisher":"Elsevier BV","issue":"7","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013139","name":"Humanities and Social Science Fund of Ministry of Education of the People's Republic of China","doi-asserted-by":"publisher","award":["24YJAZH171"],"award-info":[{"award-number":["24YJAZH171"]}],"id":[{"id":"10.13039\/501100013139","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272188"],"award-info":[{"award-number":["62272188"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Processing & Management"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.ipm.2026.104839","type":"journal-article","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T04:14:46Z","timestamp":1776831286000},"page":"104839","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["A dual-level indicative representation learning method for multimodal sarcasm detection"],"prefix":"10.1016","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3837-1688","authenticated-orcid":false,"given":"Yongcheng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3239-1089","authenticated-orcid":false,"given":"Guixin","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8747-1790","authenticated-orcid":false,"given":"Tongguan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1066-2695","authenticated-orcid":false,"given":"Mingmin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5993-3054","authenticated-orcid":false,"given":"Xiaomei","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.ipm.2026.104839_b1","article-title":"CLAVE: A deep learning model for source code authorship verification with contrastive learning and transformer encoders","volume":"62","author":"Alvarezfidalgo","year":"2025","journal-title":"Information Processing & Management"},{"issue":"4","key":"10.1016\/j.ipm.2026.104839_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103721","article-title":"Difficulty-controllable question generation over knowledge graphs: A counterfactual reasoning approach","volume":"61","author":"Bi","year":"2024","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104839_b3","series-title":"Proceedings of the international conference on global communications","first-page":"1","article-title":"Sarcasm detection in Twitter: All your products are incredibly amazing! Are they really?","author":"Bouazizi","year":"2015"},{"key":"10.1016\/j.ipm.2026.104839_b4","series-title":"Proceedings of the annual meeting of the association for computational linguistics","first-page":"2506","article-title":"Multi-modal sarcasm detection in Twitter with hierarchical fusion model","author":"Cai","year":"2019"},{"key":"10.1016\/j.ipm.2026.104839_b5","series-title":"InterCLIP-MEP: Interactive CLIP and memory-enhanced predictor for multi-modal sarcasm detection","author":"Chen","year":"2024"},{"key":"10.1016\/j.ipm.2026.104839_b6","series-title":"Proceedings of the international conference on machine learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.ipm.2026.104839_b7","series-title":"Proceedings of the international conference on learning representations","first-page":"218","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"issue":"5\u20136","key":"10.1016\/j.ipm.2026.104839_b8","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Networks"},{"issue":"1","key":"10.1016\/j.ipm.2026.104839_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103931","article-title":"Heuristic personality recognition based on fusing multiple conversations and utterance-level affection","volume":"62","author":"He","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104839_b10","series-title":"Proceedings of the international conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.ipm.2026.104839_b11","series-title":"Proceedings of the annual meeting of the association for computational linguistics","first-page":"581","article-title":"Identifying sarcasm in Twitter: A closer look","author":"Ibanez","year":"2011"},{"key":"10.1016\/j.ipm.2026.104839_b12","series-title":"Proceedings of the international conference on empirical methods in natural language processing","first-page":"1746","article-title":"Convolutional neural networks for sentence classification","author":"Kim","year":"2014"},{"issue":"3","key":"10.1016\/j.ipm.2026.104839_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.104011","article-title":"Triple contrastive learning representation boosting for supervised multiclass tasks","volume":"62","author":"Li","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104839_b14","series-title":"Proceedings of the annual meeting of the association for computational linguistics","first-page":"12373","article-title":"Multi-modal stance detection: New datasets and model","author":"Liang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104839_b15","series-title":"Proceedings of the annual meeting of the association for computational linguistics","first-page":"1767","article-title":"Multi-modal sarcasm detection via cross-modal graph convolutional network","author":"Liang","year":"2022"},{"key":"10.1016\/j.ipm.2026.104839_b16","series-title":"Proceedings of the international conference on empirical methods in natural language processing","first-page":"4995","article-title":"Towards multi-modal sarcasm detection via hierarchical congruity modeling with knowledge enhancement","author":"Liu","year":"2022"},{"issue":"3","key":"10.1016\/j.ipm.2026.104839_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.104027","article-title":"Cross-modal event extraction via visual event grounding and semantic relation filling","volume":"62","author":"Liu","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104839_b18","series-title":"Proceedings of the international conference on learning representations","first-page":"1","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"10.1016\/j.ipm.2026.104839_b19","series-title":"Proceedings of the international conference on empirical methods in natural language processing","first-page":"1383","article-title":"Modeling intra and inter-modality incongruity for multi-modal sarcasm detection","author":"Pan","year":"2020"},{"key":"10.1016\/j.ipm.2026.104839_b20","series-title":"Proceedings of the annual meeting of the association for computational linguistics","first-page":"8161","article-title":"Feature projection for improved text classification","author":"Qin","year":"2020"},{"key":"10.1016\/j.ipm.2026.104839_b21","series-title":"Proceedings of the annual meeting of the association for computational linguistics","first-page":"10834","article-title":"MMSD2.0: Towards a reliable multi-modal sarcasm detection system","author":"Qin","year":"2023"},{"key":"10.1016\/j.ipm.2026.104839_b22","series-title":"Proceedings of the eurographics conference on visualization","first-page":"73","article-title":"Visualizing time-dependent data using dynamic t-SNE","author":"Rauber","year":"2016"},{"issue":"6","key":"10.1016\/j.ipm.2026.104839_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2023.103521","article-title":"A knowledge-augmented neural network model for sarcasm detection","volume":"60","author":"Ren","year":"2023","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104839_b24","series-title":"Proceedings of the international conference on empirical methods in natural language processing","first-page":"704","article-title":"Sarcasm as contrast between a positive sentiment and negative situation","author":"Riloff","year":"2013"},{"key":"10.1016\/j.ipm.2026.104839_b25","series-title":"Proceedings of the international conference on database systems for advanced applications","first-page":"682","article-title":"A prompt-based representation individual enhancement method for Chinese idiom reading comprehension","author":"Sha","year":"2023"},{"issue":"3","key":"10.1016\/j.ipm.2026.104839_b26","article-title":"Adaptive CLIP for open-domain 3D model retrieval","volume":"62","author":"Song","year":"2025","journal-title":"Information Processing & Management"},{"issue":"3","key":"10.1016\/j.ipm.2026.104839_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103990","article-title":"Generating counterfactual negative samples for image-text matching","volume":"62","author":"Su","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104839_b28","series-title":"Proceedings of the annual meeting of the association for computational linguistics","first-page":"2468","article-title":"Dynamic routing transformer network for multimodal sarcasm detection","author":"Tian","year":"2023"},{"key":"10.1016\/j.ipm.2026.104839_b29","series-title":"Proceedings of the international conference on weblogs and social media","first-page":"162","article-title":"A great catchy name: Semi-supervised recognition of sarcastic sentences in online product reviews","author":"Tsur","year":"2010"},{"key":"10.1016\/j.ipm.2026.104839_b30","series-title":"Proceedings of the international conference on neural information processing systems","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"issue":"3","key":"10.1016\/j.ipm.2026.104839_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2022.102883","article-title":"Sememe knowledge and auxiliary information enhanced approach for sarcasm detection","volume":"59","author":"Wen","year":"2022","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104839_b32","series-title":"Proceedings of the international conference on empirical methods in natural language processing","first-page":"38","article-title":"HuggingFace\u2019s transformers: State-of-the-art natural language processing","author":"Wolf","year":"2020"},{"key":"10.1016\/j.ipm.2026.104839_b33","series-title":"Proceedings of the annual meeting of the association for computational linguistics","first-page":"14734","article-title":"Information screening whilst exploiting! Multimodal relation extraction with feature denoising and multimodal topic modeling","author":"Wu","year":"2023"},{"key":"10.1016\/j.ipm.2026.104839_b34","series-title":"Proceedings of the international conference on computer vision and pattern recognition","first-page":"3733","article-title":"Unsupervised feature learning via non-parametric instance discrimination","author":"Wu","year":"2018"},{"key":"10.1016\/j.ipm.2026.104839_b35","series-title":"Proceedings of the 2024 joint international conference on computational linguistics, language resources and evaluation, LREC\/COLING 2024, 20-25 May, 2024, Torino, Italy","first-page":"2493","article-title":"Breakthrough from nuance and inconsistency: Enhancing multimodal sarcasm detection with context-aware self-attention fusion and word weight calculation","author":"Xue","year":"2024"},{"issue":"3","key":"10.1016\/j.ipm.2026.104839_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.104015","article-title":"Analysis of user experience in low-resource languages: A case study of the Uzbek language google play reviews","volume":"62","author":"Yusufu","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104839_b37","series-title":"Proceedings of the international conference on computational linguistics","first-page":"2449","article-title":"Tweet sarcasm detection using deep neural network","author":"Zhang","year":"2016"},{"key":"10.1016\/j.ipm.2026.104839_b38","series-title":"Proceedings of the international conference on computer vision and pattern recognition","first-page":"2921","article-title":"Learning deep features for discriminative localization","author":"Zhou","year":"2016"},{"key":"10.1016\/j.ipm.2026.104839_b39","series-title":"2025 IEEE international conference on acoustics, speech and signal processing, ICASSP 2025, Hyderabad, India, April 6-11, 2025","first-page":"1","article-title":"LDGNet: LLMs debate-guided network for multimodal sarcasm detection","author":"Zhou","year":"2025"},{"key":"10.1016\/j.ipm.2026.104839_b40","series-title":"Proceedings of the 2024 joint international conference on computational linguistics, language resources and evaluation, LREC\/COLING 2024, 20-25 May, 2024, Torino, Italy","first-page":"16581","article-title":"Towards multi-modal sarcasm detection via disentangled multi-grained multi-modal distilling","author":"Zhu","year":"2024"},{"key":"10.1016\/j.ipm.2026.104839_b41","series-title":"Proceedings of the international conference on empirical methods in natural language processing","first-page":"2900","article-title":"DGLF: A dual graph-based learning framework for multi-modal sarcasm detection","author":"Zhu","year":"2024"},{"key":"10.1016\/j.ipm.2026.104839_b42","series-title":"Proceedings of the international joint conference on artificial intelligence","first-page":"6687","article-title":"TFCD: Towards multi-modal sarcasm detection via training-free counterfactual debiasing","author":"Zhu","year":"2024"}],"container-title":["Information Processing & Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S030645732600230X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S030645732600230X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:39:29Z","timestamp":1783154369000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S030645732600230X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":42,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,11]]}},"alternative-id":["S030645732600230X"],"URL":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104839","relation":{},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A dual-level indicative representation learning method for multimodal sarcasm detection","name":"articletitle","label":"Article Title"},{"value":"Information Processing & Management","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104839","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104839"}}