{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:20:07Z","timestamp":1778692807400,"version":"3.51.4"},"reference-count":109,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/taffc.2025.3612205","type":"journal-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T17:37:51Z","timestamp":1758303471000},"page":"2526-2544","source":"Crossref","is-referenced-by-count":3,"title":["Spoken in Jest, Detected in Earnest: A Systematic Review of Sarcasm Recognition\u2014Multimodal Fusion, Challenges, and Future Prospects"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0870-6721","authenticated-orcid":false,"given":"Xiyuan","family":"Gao","sequence":"first","affiliation":[{"name":"Campus Fryslân, University of Groningen, Leeuwarden, CE, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4277-4851","authenticated-orcid":false,"given":"Shekhar","family":"Nayak","sequence":"additional","affiliation":[{"name":"Campus Fryslân, University of Groningen, Leeuwarden, CE, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7631-5063","authenticated-orcid":false,"given":"Matt","family":"Coler","sequence":"additional","affiliation":[{"name":"Campus Fryslân, University of Groningen, Leeuwarden, CE, The Netherlands"}]}],"member":"263","reference":[{"key":"ref1","first-page":"295","article-title":"Irony and use-mention distinction","volume-title":"Radical Pragmatics","author":"Sperber","year":"1981"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0378-2166(95)00067-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511813085"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/089124189018003004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/01638539509544916"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1006\/brln.1999.2124"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1163\/9789004368811_003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1037\/0096-3445.113.1.112"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awn314"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.rasd.2012.08.005"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1005120109296"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1121\/1.3177275"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0023830911402608"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-761"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-507"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-239"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3124420"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09791-8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WiSPNET.2017.8300120"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1000097"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1455"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDECOM.2011.5738540"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3083522"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.maiworkshop-1.9"},{"key":"ref25","first-page":"18794","article-title":"CMMA: Benchmarking multi-affection detection in chinese multi-modal conversations","volume-title":"Proc. 37th Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10978"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.401"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109924"},{"key":"ref29","first-page":"6992","article-title":"A multimodal corpus for emotion recognition in sarcasm","volume-title":"Proc. 13th Lang. Resour. Eval. Conf.","author":"Ray","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/0163853X.2019.1637204"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-2166(99)00116-2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1037\/0096-3445.124.1.3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1177\/0956797615574699"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2021.3069097"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3458380.3458414"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73706-5_2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12397-9_21"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT51525.2021.9580028"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17534"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1037\/h0031619"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11323"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-27524-1_34"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"12972","DOI":"10.21437\/SpeechProsody.2010-243","article-title":"Characterization of emotions using the dynamics of prosodic features","volume-title":"Proc. SpeechProsody","author":"Rao","year":"2010"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/confluence.2017.7943246"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-56"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88480-2_66"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/1653696"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-12122-9"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3390\/app122111235"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00062"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/APSIT58554.2023.10201731"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICDS62089.2024.10756398"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111457"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-023-03224-y"},{"issue":"14","key":"ref56","first-page":"356","article-title":"Voice-based sarcasm detection in Kannada language","volume-title":"Int. J. Intell. Syst. Appl. Eng.","volume":"12","author":"Manohar","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115476"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref59","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.01.005"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"issue":"9\u201310","key":"ref63","first-page":"341","article-title":"PRAAT, a system for doing phonetics by computer","volume":"5","author":"Boersma","year":"2001","journal-title":"Glot Int."},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.25080\/majora-7b98e3ed-003"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3279145"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3298328"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1121\/2.0001918"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1525\/9780520940420-020"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612528"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102085"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref75","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Tan","year":"2019"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1515\/humr.2003.012"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1177\/0261927X04269587"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0163211"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3649447"},{"key":"ref83","volume-title":"Statistical Methods for Meta-Analysis","author":"Hedges","year":"1985"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1002\/sim.1186"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/0197-2456(86)90046-2"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.3233\/978-1-60750-072-8-51"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-0068.2010.00822.x"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3379877"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-43"},{"key":"ref91","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref92","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2025.3604806"},{"key":"ref94","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/s10919-021-00385-z"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1037\/cep0000223"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.pragma.2022.09.007"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.pragma.2021.05.007"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.jml.2017.10.001"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.11.003"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1080\/00207590244000106"},{"key":"ref102","first-page":"259","article-title":"Categorical and schematic organization in memory","volume-title":"Memory, Organization, and Structure","author":"Mandler","year":"1979"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.pragma.2013.08.016"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/3635311"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAIS62903.2024.10811714"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3678957.3685723"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref109","first-page":"69","article-title":"The fisher corpus: A resource for the next generations of speech-to-text","volume-title":"Proc. 4th Int. Conf. Lang. Resour. Eval.","author":"Cieri","year":"2004"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11269911\/11173951.pdf?arnumber=11173951","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:58:28Z","timestamp":1764269908000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11173951\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":109,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2025.3612205","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}