{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:13:59Z","timestamp":1781586839411,"version":"3.54.5"},"reference-count":28,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011033","name":"State Agency of Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Standards & Interfaces"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.csi.2026.104130","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T17:02:24Z","timestamp":1768582944000},"page":"104130","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["A Dynamic Multimodal Causal Graph framework for standardized Emotion Recognition in Conversations"],"prefix":"10.1016","volume":"97","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7317-7145","authenticated-orcid":false,"given":"Ronghao","family":"Pan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3651-2660","authenticated-orcid":false,"given":"Jos\u00e9 Antonio","family":"Garc\u00eda-D\u00edaz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2457-1791","authenticated-orcid":false,"given":"Rafael","family":"Valencia-Garc\u00eda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.csi.2026.104130_b1","doi-asserted-by":"crossref","first-page":"100943","DOI":"10.1109\/ACCESS.2019.2929050","article-title":"Emotion recognition in conversation: Research challenges, datasets, and recent advances","volume":"7","author":"Poria","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.csi.2026.104130_b2","doi-asserted-by":"crossref","unstructured":"N. Majumder, S. Poria, D. Hazarika, R. Mihalcea, A. Gelbukh, et al., Dialoguernn: An attentive rnn for emotion detection in conversations, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, 2019, pp. 6818\u20136825.","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"10.1016\/j.csi.2026.104130_b3","series-title":"Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation","author":"Ghosal","year":"2019"},{"key":"10.1016\/j.csi.2026.104130_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111969","article-title":"Speaker-aware cognitive network with cross-modal attention for multimodal emotion recognition in conversation","volume":"296","author":"Guo","year":"2024","journal-title":"Knowl.-Based Syst."},{"issue":"4","key":"10.1016\/j.csi.2026.104130_b5","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"IEMOCAP: Interactive emotional dyadic motion capture database","volume":"42","author":"Busso","year":"2008","journal-title":"Lang. Resour. Eval."},{"key":"10.1016\/j.csi.2026.104130_b6","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"527","article-title":"MELD: A multimodal multi-party dataset for emotion recognition in conversations","author":"Poria","year":"2019"},{"key":"10.1016\/j.csi.2026.104130_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126866","article-title":"A review of multimodal emotion recognition from datasets, preprocessing, features, and fusion methods","volume":"561","author":"Pan","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.csi.2026.104130_b8","series-title":"Handbook of social psychophysiology","first-page":"164","article-title":"The argument and evidence about universals in facial expressions","volume":"Vol. 143","author":"Ekman","year":"1989"},{"issue":"3","key":"10.1016\/j.csi.2026.104130_b9","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1037\/0022-3514.37.3.345","article-title":"Affective space is bipolar.","volume":"37","author":"Russell","year":"1979","journal-title":"J. Pers. Soc. Psychol."},{"issue":"4","key":"10.1016\/j.csi.2026.104130_b10","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/BF02686918","article-title":"Pleasure-arousal-dominance: A general framework for describing and measuring individual differences in temperament","volume":"14","author":"Mehrabian","year":"1996","journal-title":"Curr. Psychol."},{"key":"10.1016\/j.csi.2026.104130_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.csi.2024.103895","article-title":"People 4.0 \u2013 a model for human-in-the-loop CPS-based systems","volume":"91","author":"Fernandes","year":"2025","journal-title":"Comput. Stand. Interfaces"},{"key":"10.1016\/j.csi.2026.104130_b12","article-title":"Advanced speech emotion recognition utilizing optimized equivariant quantum convolutional neural network for accurate emotional state classification","volume":"316","author":"Balachandran","year":"2025","journal-title":"Knowl.-Based Syst."},{"issue":"12","key":"10.1016\/j.csi.2026.104130_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.asej.2024.103038","article-title":"Emotion-net: Automatic emotion recognition system using optimal feature selection-based hidden markov CNN model","volume":"15","author":"Krishna","year":"2024","journal-title":"Ain Shams Eng. J."},{"key":"10.1016\/j.csi.2026.104130_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.csi.2024.103856","article-title":"Spanish meacorpus 2023: A multimodal speech\u2013text corpus for emotion analysis in spanish from natural environments","volume":"90","author":"Pan","year":"2024","journal-title":"Comput. Stand. Interfaces"},{"issue":"5","key":"10.1016\/j.csi.2026.104130_b15","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1109\/MIS.2020.2992799","article-title":"The hourglass model revisited","volume":"35","author":"Susanto","year":"2020","journal-title":"IEEE Intell. Syst."},{"key":"10.1016\/j.csi.2026.104130_b16","doi-asserted-by":"crossref","unstructured":"D. Hu, L. Wei, X. Huai, DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversations, in: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2021, pp. 7042\u20137052.","DOI":"10.18653\/v1\/2021.acl-long.547"},{"key":"10.1016\/j.csi.2026.104130_b17","doi-asserted-by":"crossref","unstructured":"S. Poria, E. Cambria, D. Hazarika, N. Majumder, A. Zadeh, et al., Context-dependent sentiment analysis in user-generated videos, in: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2017, pp. 873\u2013883.","DOI":"10.18653\/v1\/P17-1081"},{"key":"10.1016\/j.csi.2026.104130_b18","doi-asserted-by":"crossref","unstructured":"D. Hazarika, S. Poria, A. Zadeh, E. Cambria, L.-P. Morency, et al., Conversational memory network for emotion recognition in dyadic dialogue videos, in: Proceedings of the Conference. Association for Computational Linguistics. North American Chapter. Meeting, Vol. 2018, 2018, p. 2122.","DOI":"10.18653\/v1\/N18-1193"},{"key":"10.1016\/j.csi.2026.104130_b19","series-title":"Cosmic: Commonsense knowledge for emotion identification in conversations","author":"Ghosal","year":"2020"},{"key":"10.1016\/j.csi.2026.104130_b20","doi-asserted-by":"crossref","unstructured":"W. Shen, J. Chen, X. Quan, Z. Xie, DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition, in: AAAI Conference on Artificial Intelligence, 2020.","DOI":"10.1609\/aaai.v35i15.17625"},{"key":"10.1016\/j.csi.2026.104130_b21","doi-asserted-by":"crossref","unstructured":"Z. Dai, Z. Yang, Y. Yang, J.G. Carbonell, Q. Le, R. Salakhutdinov, Transformer-xl: Attentive language models beyond a fixed-length context, in: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019, pp. 2978\u20132988.","DOI":"10.18653\/v1\/P19-1285"},{"key":"10.1016\/j.csi.2026.104130_b22","doi-asserted-by":"crossref","unstructured":"D. Hazarika, S. Poria, R. Mihalcea, E. Cambria, R. Zimmermann, Icon: Interactive conversational memory network for multimodal emotion detection, in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018, pp. 2594\u20132604.","DOI":"10.18653\/v1\/D18-1280"},{"key":"10.1016\/j.csi.2026.104130_b23","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"issue":"19","key":"10.1016\/j.csi.2026.104130_b24","doi-asserted-by":"crossref","DOI":"10.3390\/math13193088","article-title":"LightFakeDetect: A lightweight model for deepfake detection in videos that focuses on facial regions","volume":"13","author":"AlMuhaideb","year":"2025","journal-title":"Mathematics"},{"key":"10.1016\/j.csi.2026.104130_b25","series-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation","article-title":"EmotionLines: An emotion corpus of multi-party conversations","author":"Hsu","year":"2018"},{"key":"10.1016\/j.csi.2026.104130_b26","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/j.inffus.2022.10.009","article-title":"Dynamic interactive multiview memory network for emotion recognition in conversation","volume":"91","author":"Wen","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.csi.2026.104130_b27","series-title":"2023 IEEE 2nd International Conference on Electrical Engineering, Big Data and Algorithms","first-page":"373","article-title":"Multimodal emotion recognition based on feature fusion and residual connection","author":"Du","year":"2023"},{"key":"10.1016\/j.csi.2026.104130_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.csi.2025.103990","article-title":"Spanish MTLHateCorpus 2023: Multi-task learning for hate speech detection to identify speech type, target, target group and intensity","volume":"94","author":"Pan","year":"2025","journal-title":"Comput. Stand. Interfaces"}],"container-title":["Computer Standards & Interfaces"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0920548926000048?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0920548926000048?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T02:09:08Z","timestamp":1773972548000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0920548926000048"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":28,"alternative-id":["S0920548926000048"],"URL":"https:\/\/doi.org\/10.1016\/j.csi.2026.104130","relation":{},"ISSN":["0920-5489"],"issn-type":[{"value":"0920-5489","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A Dynamic Multimodal Causal Graph framework for standardized Emotion Recognition in Conversations","name":"articletitle","label":"Article Title"},{"value":"Computer Standards & Interfaces","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.csi.2026.104130","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 B.V.","name":"copyright","label":"Copyright"}],"article-number":"104130"}}