{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T01:49:30Z","timestamp":1784684970031,"version":"3.55.0"},"reference-count":41,"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":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376027"],"award-info":[{"award-number":["62376027"]}],"id":[{"id":"10.13039\/501100001809","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.2026.132291","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T15:27:46Z","timestamp":1774970866000},"page":"132291","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["HC-CoT: A hierarchical causal chain-of-thought framework for multimodal sarcasm detection"],"prefix":"10.1016","volume":"322","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3307-4017","authenticated-orcid":false,"given":"Tianyu","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6411-7035","authenticated-orcid":false,"given":"Junlong","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0106-0478","authenticated-orcid":false,"given":"Ling-Ang","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8660-3608","authenticated-orcid":false,"given":"Dawei","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132291_bib0001","series-title":"Proceedings of the 5th workshop on computational approaches to subjectivity, sentiment and social media analysis (WASSA 2014)","first-page":"50","article-title":"Modelling sarcasm in twitter, a novel approach","author":"Barbieri","year":"2014"},{"key":"10.1016\/j.eswa.2026.132291_bib0002","series-title":"Proceedings of the 57th annual meeting of the association for computational linguistics (ACL 2019)","first-page":"2506","article-title":"Multi-modal sarcasm detection in twitter with hierarchical fusion model","author":"Cai","year":"2019"},{"issue":"2","key":"10.1016\/j.eswa.2026.132291_bib0003","first-page":"1","article-title":"InterCLIP-MEP: Interactive CLIP and memory-enhanced predictor for multi-modal sarcasm detection","volume":"22","author":"Chen","year":"2026","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"key":"10.1016\/j.eswa.2026.132291_bib0004","article-title":"An adaptive multimodal semantic knowledge enhanced framework for sarcasm detection","volume":"298","author":"Dong","year":"2026","journal-title":"Expert Systems with Applications (ESWA)"},{"key":"10.1016\/j.eswa.2026.132291_bib0005","series-title":"Proceedings of the international conference on learning representations (ICLR 2020)","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.eswa.2026.132291_bib0006","series-title":"Proceedings of the 7th workshop on computational approaches to subjectivity, sentiment and social media analysis (WASSA 2016)","first-page":"161","article-title":"Fracking sarcasm using neural network","author":"Ghosh","year":"2016"},{"key":"10.1016\/j.eswa.2026.132291_bib0007","series-title":"Proceedings of the 49th annual meeting of the association for computational linguistics: Human language technologies (ACL-HLT 2011)","first-page":"581","article-title":"Identifying sarcasm in twitter: A closer look","author":"Gonz\u00e1lez-Ib\u00e1nez","year":"2011"},{"key":"10.1016\/j.eswa.2026.132291_bib0008","article-title":"Mian: Multi-head incongruity aware attention network with transfer learning for sarcasm detection","volume":"263","author":"Guan","year":"2025","journal-title":"Expert Systems with Applications (ESWA)"},{"key":"10.1016\/j.eswa.2026.132291_bib0009","series-title":"Proceedings of the 31st international conference on computational linguistics (COLING 2025)","first-page":"1754","article-title":"Multi-view incongruity learning for multimodal sarcasm detection","author":"Guo","year":"2025"},{"key":"10.1016\/j.eswa.2026.132291_bib0010","series-title":"Proceedings of the AAAI conference on artificial intelligence (AAAI 2024)","first-page":"18354","article-title":"Debiasing multimodal sarcasm detection with contrastive learning","volume":"vol. 38","author":"Jia","year":"2024"},{"key":"10.1016\/j.eswa.2026.132291_bib0011","series-title":"Proceedings of the 40th international conference on machine learning (ICML 2023)","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.eswa.2026.132291_bib0012","series-title":"Proceedings of the 31st international conference on computational linguistics (COLING 2025)","first-page":"380","article-title":"Ambiguity-aware multi-level incongruity fusion network for multi-modal sarcasm detection","author":"Li","year":"2025"},{"key":"10.1016\/j.eswa.2026.132291_bib0013","series-title":"Proceedings of the 29th ACM international conference on multimedia (ACM MM 2021)","first-page":"4707","article-title":"Multi-modal sarcasm detection with interactive in-modal and cross-modal graphs","author":"Liang","year":"2021"},{"key":"10.1016\/j.eswa.2026.132291_bib0014","series-title":"Proceedings of the 60th annual meeting of the association for computational linguistics (ACL 2022), volume 1: Long papers","first-page":"1767","article-title":"Multi-modal sarcasm detection via cross-modal graph convolutional network","author":"Liang","year":"2022"},{"key":"10.1016\/j.eswa.2026.132291_bib0015","series-title":"Proceedings of the 2022 conference on empirical methods in natural language processing (EMNLP 2022)","first-page":"4995","article-title":"Towards multi-modal sarcasm detection via hierarchical congruity modeling with knowledge enhancement","author":"Liu","year":"2022"},{"key":"10.1016\/j.eswa.2026.132291_bib0016","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. arXiv: 1907.11692."},{"key":"10.1016\/j.eswa.2026.132291_bib0017","series-title":"Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval (SIGIR 2021)","first-page":"1844","article-title":"Affective dependency graph for sarcasm detection","author":"Lou","year":"2021"},{"key":"10.1016\/j.eswa.2026.132291_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102203","article-title":"Fact-sentiment incongruity combination network for multimodal sarcasm detection","volume":"104","author":"Lu","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132291_bib0019","series-title":"Findings of the association for computational linguistics: EMNLP 2020 (findings of EMNLP 2020)","first-page":"1383","article-title":"Modeling intra and inter-modality incongruity for multi-modal sarcasm detection","author":"Pan","year":"2020"},{"key":"10.1016\/j.eswa.2026.132291_bib0020","series-title":"Proceedings of the AAAI conference on artificial intelligence (AAAI 2023)","first-page":"9507","article-title":"Mutual-enhanced incongruity learning network for multi-modal sarcasm detection","volume":"vol. 37","author":"Qiao","year":"2023"},{"key":"10.1016\/j.eswa.2026.132291_bib0021","series-title":"Findings of the association for computational linguistics: ACL 2023 (findings of ACL 2023)","first-page":"10834","article-title":"MMSD2.0: Towards a reliable multi-modal sarcasm detection system","author":"Qin","year":"2023"},{"key":"10.1016\/j.eswa.2026.132291_bib0022","series-title":"Proceedings of the 8th ACM international conference on web search and data mining (WSDM 2015)","first-page":"97","article-title":"Sarcasm detection on twitter: A behavioral modeling approach","author":"Rajadesingan","year":"2015"},{"issue":"1","key":"10.1016\/j.eswa.2026.132291_bib0023","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1007\/s10579-012-9196-x","article-title":"A multidimensional approach for detecting irony in twitter","volume":"47","author":"Reyes","year":"2013","journal-title":"Language Resources and Evaluation"},{"key":"10.1016\/j.eswa.2026.132291_bib0024","series-title":"Proceedings of the 24th ACM international conference on multimedia (ACM MM 2016)","first-page":"1136","article-title":"Detecting sarcasm in multimodal social platforms","author":"Schifanella","year":"2016"},{"key":"10.1016\/j.eswa.2026.132291_bib0025","series-title":"Proceedings of the 2024 conference of the North American chapter of the association for computational linguistics: Human language technologies (NAACL 2024) (volume 1: Long papers)","first-page":"1732","article-title":"Leveraging generative large language models with visual instruction and demonstration retrieval for multimodal sarcasm detection","author":"Tang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132291_bib0026","series-title":"Proceedings of the 56th annual meeting of the association for computational linguistics (ACL 2018), volume 1: Long papers","first-page":"1010","article-title":"Reasoning with sarcasm by reading in-between","author":"Tay","year":"2018"},{"key":"10.1016\/j.eswa.2026.132291_bib0027","series-title":"Proceedings of the 61st annual meeting of the association for computational linguistics (ACL 2023), volume 1: Long papers","first-page":"2468","article-title":"Dynamic routing transformer network for multimodal sarcasm detection","author":"Tian","year":"2023"},{"key":"10.1016\/j.eswa.2026.132291_bib0028","series-title":"Proceedings of the fourth international AAAI conference on web and social media (ICWSM 2010)","first-page":"162","article-title":"ICWSM\u2014a great catchy name: Semi-supervised recognition of sarcastic sentences in online product reviews","author":"Tsur","year":"2010"},{"key":"10.1016\/j.eswa.2026.132291_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102132","article-title":"Cross-modal incongruity aligning and collaborating for multi-modal sarcasm detection","volume":"103","author":"Wang","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132291_bib0030","series-title":"Proceedings of the AAAI conference on artificial intelligence (AAAI 2023)","first-page":"4702","article-title":"Augmenting affective dependency graph via iterative incongruity graph learning for sarcasm detection","volume":"vol. 37","author":"Wang","year":"2023"},{"key":"10.1016\/j.eswa.2026.132291_bib0031","series-title":"Proceedings of the AAAI conference on artificial intelligence (AAAI 2024)","first-page":"9151","article-title":"G2SAM: Graph-based global semantic awareness method for multimodal sarcasm detection","volume":"vol. 38","author":"Wei","year":"2024"},{"key":"10.1016\/j.eswa.2026.132291_bib0032","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR 2023)","first-page":"2540","article-title":"Dip: Dual incongruity perceiving network for sarcasm detection","author":"Wen","year":"2023"},{"key":"10.1016\/j.eswa.2026.132291_bib0033","series-title":"Findings of the association for computational linguistics: EMNLP 2025 (findings of EMNLP 2025)","first-page":"3805","article-title":"Beyond spurious signals: Debiasing multimodal large language models via counterfactual inference and adaptive expert routing","author":"Wu","year":"2025"},{"key":"10.1016\/j.eswa.2026.132291_bib0034","article-title":"Multimodal sarcasm detection based on sentiment-clue inconsistency global detection fusion network","volume":"275","author":"Xi","year":"2025","journal-title":"Expert Systems with Applications (ESWA)"},{"key":"10.1016\/j.eswa.2026.132291_bib0035","series-title":"Proceedings of the web conference 2019 (WWW 2019)","first-page":"2115","article-title":"Sarcasm detection with self-matching networks and low-rank bilinear pooling","author":"Xiong","year":"2019"},{"key":"10.1016\/j.eswa.2026.132291_bib0036","series-title":"Proceedings of the 58th annual meeting of the association for computational linguistics (ACL 2020)","first-page":"3777","article-title":"Reasoning with multimodal sarcastic tweets via modeling cross-modality contrast and semantic association","author":"Xu","year":"2020"},{"key":"10.1016\/j.eswa.2026.132291_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101921","article-title":"KnowleNet: Knowledge fusion network for multimodal sarcasm detection","volume":"100","author":"Yue","year":"2023","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132291_bib0038","series-title":"Proceedings of COLING 2016: The 26th international conference on computational linguistics (COLING 2016)","first-page":"2449","article-title":"Tweet sarcasm detection using deep neural network","author":"Zhang","year":"2016"},{"key":"10.1016\/j.eswa.2026.132291_bib0039","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR 2021)","first-page":"5579","article-title":"VinVL: Revisiting visual representations in vision-language models","author":"Zhang","year":"2021"},{"issue":"20","key":"10.1016\/j.eswa.2026.132291_bib0040","doi-asserted-by":"crossref","first-page":"3250","DOI":"10.3390\/math13203250","article-title":"Beyond spurious cues: Adaptive multi-modal fusion via mixture-of-experts for robust sarcasm detection","volume":"13","author":"Zhao","year":"2025","journal-title":"Mathematics"},{"key":"10.1016\/j.eswa.2026.132291_bib0041","series-title":"Proceedings of the international joint conference on artificial intelligence (IJCAI 2024)","first-page":"6687","article-title":"TFCD: Towards multi-modal sarcasm detection via training-free counterfactual debiasing","author":"Zhu","year":"2024"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426012042?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426012042?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T23:59:54Z","timestamp":1781308794000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426012042"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":41,"alternative-id":["S0957417426012042"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132291","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":"HC-CoT: A hierarchical causal chain-of-thought framework for multimodal sarcasm detection","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132291","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":"132291"}}