{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:57:24Z","timestamp":1777874244966,"version":"3.51.4"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T00:00:00Z","timestamp":1775865600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.neucom.2026.133622","type":"journal-article","created":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T17:36:34Z","timestamp":1776015394000},"page":"133622","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["CMSA: Addressing semantic discrepancy and context dependency in multimodal sentiment analysis"],"prefix":"10.1016","volume":"685","author":[{"given":"Jianing","family":"Zhao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1172-1789","authenticated-orcid":false,"given":"Ou","family":"Deng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1325-4275","authenticated-orcid":false,"given":"Qun","family":"Jin","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"7","key":"10.1016\/j.neucom.2026.133622_bib0005","doi-asserted-by":"crossref","first-page":"5731","DOI":"10.1007\/s10462-022-10144-1","article-title":"A survey on sentiment analysis methods, applications, and challenges","volume":"55","author":"Wankhade","year":"2022","journal-title":"Artif. Intell. Rev."},{"issue":"1","key":"10.1016\/j.neucom.2026.133622_bib0010","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1146\/annurev-linguistics-011415-040518","article-title":"Sentiment analysis: an overview from linguistics","volume":"2","author":"Taboada","year":"2016","journal-title":"Annu. Rev. Linguist."},{"issue":"1\u20132","key":"10.1016\/j.neucom.2026.133622_bib0015","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/1500000011","article-title":"Opinion mining and sentiment analysis","volume":"2","author":"Pang","year":"2008","journal-title":"Found. Trends Inf. Retr."},{"issue":"3","key":"10.1016\/j.neucom.2026.133622_bib0020","doi-asserted-by":"crossref","first-page":"1195","DOI":"10.1109\/TAFFC.2020.2981446","article-title":"Deep facial expression recognition: a survey","volume":"13","author":"Li","year":"2020","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"2","key":"10.1016\/j.neucom.2026.133622_bib0025","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","article-title":"The Geneva minimalistic acoustic parameter set (GEMAPS) for voice research and affective computing","volume":"7","author":"Eyben","year":"2015","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"1","key":"10.1016\/j.neucom.2026.133622_bib0030","doi-asserted-by":"crossref","first-page":"73","DOI":"10.38094\/jastt20291","article-title":"Multimodal emotion recognition using deep learning","volume":"2","author":"Abdullah","year":"2021","journal-title":"J. Appl. Sci. Technol. Trends"},{"key":"10.1016\/j.neucom.2026.133622_bib0035","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"9100","article-title":"Tailor versatile multi-modal learning for multi-label emotion recognition","volume":"vol. 36","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neucom.2026.133622_bib0040","author":"Han"},{"key":"10.1016\/j.neucom.2026.133622_bib0045","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.inffus.2017.02.003","article-title":"A review of affective computing: from unimodal analysis to multimodal fusion","volume":"37","author":"Poria","year":"2017","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.133622_bib0050","series-title":"Proceedings of the Conference Association for Computational Linguistics Meeting","first-page":"6558","article-title":"Multimodal transformer for unaligned multimodal language sequences","volume":"vol. 2019","author":"Tsai","year":"2019"},{"issue":"1","key":"10.1016\/j.neucom.2026.133622_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2023.103538","article-title":"Coordinated-joint translation fusion framework with sentiment-interactive graph convolutional networks for multimodal sentiment analysis","volume":"61","author":"Lu","year":"2024","journal-title":"Inf. Process. Manag."},{"key":"10.1016\/j.neucom.2026.133622_bib0060","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2575","article-title":"Dynamic multimodal fusion","author":"Xue","year":"2023"},{"key":"10.1016\/j.neucom.2026.133622_bib0065","author":"Li"},{"key":"10.1016\/j.neucom.2026.133622_bib0070","doi-asserted-by":"crossref","first-page":"6301","DOI":"10.1109\/TMM.2022.3207572","article-title":"Robust multimodal sentiment analysis via tag encoding of uncertain missing modalities","volume":"25","author":"Zeng","year":"2022","journal-title":"IEEE Trans. Multimed."},{"issue":"13s","key":"10.1016\/j.neucom.2026.133622_bib0075","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3586075","article-title":"Multimodal sentiment analysis: a survey of methods, trends, and challenges","volume":"55","author":"Das","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.133622_bib0080","article-title":"UCMIB-PNS: balancing sufficiency and necessity with probabilistic causality and cross-modal uncertainty in multimodal sentiment analysis","author":"Chen","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.neucom.2026.133622_bib0085","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101847","article-title":"Emotion recognition from unimodal to multimodal analysis: a review","volume":"99","author":"Ezzameli","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.133622_bib0090","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.neucom.2026.133622_bib0095","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Memory fusion network for multi-view sequential learning","volume":"vol. 32","author":"Zadeh","year":"2018"},{"key":"10.1016\/j.neucom.2026.133622_bib0100","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2453","article-title":"Deep multi-model fusion for single-image dehazing","author":"Deng","year":"2019"},{"key":"10.1016\/j.neucom.2026.133622_bib0105","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102725","article-title":"ATCAF: attention-based causality-aware fusion network for multimodal sentiment analysis","volume":"114","author":"Huang","year":"2025","journal-title":"Inf. Fusion"},{"issue":"6","key":"10.1016\/j.neucom.2026.133622_bib0110","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3736415","article-title":"Actual cause guided adaptive gradient scaling for balanced multimodal sentiment analysis","volume":"21","author":"Chen","year":"2025","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"issue":"1","key":"10.1016\/j.neucom.2026.133622_bib0115","first-page":"1","article-title":"PAMOE-MSA: polarity-aware mixture of experts network for multimodal sentiment analysis","volume":"14","author":"Huang","year":"2025","journal-title":"Int. J. Multimed. Inf. Retr."},{"issue":"4","key":"10.1016\/j.neucom.2026.133622_bib0120","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1007\/s40747-025-01806-y","article-title":"H 2 can: heterogeneous hypergraph attention network with counterfactual learning for multimodal sentiment analysis","volume":"11","author":"Huang","year":"2025","journal-title":"Complex Intell. Syst."},{"issue":"4","key":"10.1016\/j.neucom.2026.133622_bib0125","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1007\/s13735-024-00347-3","article-title":"Multi-modal emotion recognition using tensor decomposition fusion and self-supervised multi-tasking","volume":"13","author":"Wang","year":"2024","journal-title":"Int. J. Multimed. Inf. Retr."},{"issue":"18","key":"10.1016\/j.neucom.2026.133622_bib0130","doi-asserted-by":"crossref","first-page":"56039","DOI":"10.1007\/s11042-023-17347-w","article-title":"Emotion recognition based on brain-like multimodal hierarchical perception","volume":"83","author":"Zhu","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.neucom.2026.133622_bib0135","series-title":"International Conference on Machine Learning","first-page":"3800","article-title":"Improving the gating mechanism of recurrent neural networks","author":"Gu","year":"2020"},{"issue":"11","key":"10.1016\/j.neucom.2026.133622_bib0140","doi-asserted-by":"crossref","first-page":"3665","DOI":"10.1016\/j.patcog.2014.05.003","article-title":"Dynamic selection of classifiers\u2014a comprehensive review","volume":"47","author":"Britto Jr","year":"2014","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133622_bib0145","series-title":"ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"4477","article-title":"Gated mechanism for attention based multi modal sentiment analysis","author":"Kumar","year":"2020"},{"key":"10.1016\/j.neucom.2026.133622_bib0150","doi-asserted-by":"crossref","first-page":"3375","DOI":"10.1109\/TMM.2022.3160060","article-title":"Multimodal sentiment analysis with image-text interaction network","volume":"25","author":"Zhu","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.133622_bib0155","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101973","article-title":"Modality translation-based multimodal sentiment analysis under uncertain missing modalities","volume":"101","author":"Liu","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.133622_bib0160","article-title":"Tempo: training-time equilibration of modalities for per-sample optimization in multimodal sentiment","author":"Zhao","year":"2026","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.neucom.2026.133622_bib0165","doi-asserted-by":"crossref","DOI":"10.1016\/j.array.2025.100445","article-title":"Raft: robust adversarial fusion transformer for multimodal sentiment analysis","author":"Wang","year":"2025","journal-title":"Array"},{"issue":"3","key":"10.1016\/j.neucom.2026.133622_bib0170","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s12559-025-10463-9","article-title":"Contrastive-based removal of negative information in multimodal emotion analysis","volume":"17","author":"Wang","year":"2025","journal-title":"Cogn. Comput."},{"issue":"5","key":"10.1016\/j.neucom.2026.133622_bib0175","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/MIS.2025.3597120","article-title":"A generative random modality dropout framework for robust multimodal emotion recognition","volume":"40","author":"Zhang","year":"2025","journal-title":"IEEE Intell. Syst."},{"issue":"8","key":"10.1016\/j.neucom.2026.133622_bib0180","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1007\/s40747-025-01931-8","article-title":"EMVAS: end-to-end multimodal emotion visualization analysis system","volume":"11","author":"Zhu","year":"2025","journal-title":"Complex Intell. Syst."},{"key":"10.1016\/j.neucom.2026.133622_bib0185","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103268","article-title":"RMER-DT: robust multimodal emotion recognition in conversational contexts based on diffusion and transformers","volume":"123","author":"Zhu","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.133622_bib0190","article-title":"CIME: contextual interaction-based multimodal emotion analysis with enhanced semantic information","author":"Wang","year":"2025","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"10.1016\/j.neucom.2026.133622_bib0195","series-title":"International Conference on Learning Representations","article-title":"Outrageously large neural networks: the sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017"},{"key":"10.1016\/j.neucom.2026.133622_bib0200","series-title":"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)","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.neucom.2026.133622_bib0205","series-title":"Supervised Sequence Labelling with Recurrent Neural Networks","first-page":"37","article-title":"Long short-term memory","author":"Graves","year":"2012"},{"key":"10.1016\/j.neucom.2026.133622_bib0210","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133622_bib0215","author":"Poria"},{"key":"10.1016\/j.neucom.2026.133622_bib0220","series-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"2247","article-title":"Efficient low-rank multimodal fusion with modality-specific factors","author":"Liu","year":"2018"},{"key":"10.1016\/j.neucom.2026.133622_bib0225","series-title":"International Conference on Representation Learning","article-title":"Learning factorized multimodal representations","author":"Tsai","year":"2019"},{"key":"10.1016\/j.neucom.2026.133622_bib0230","series-title":"Proceedings of the 28th ACM International Conference on Multimedia","first-page":"1122","article-title":"MISA: modality-invariant and-specific representations for multimodal sentiment analysis","author":"Hazarika","year":"2020"},{"key":"10.1016\/j.neucom.2026.133622_bib0235","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"10790","article-title":"Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis","volume":"vol. 35","author":"Yu","year":"2021"},{"key":"10.1016\/j.neucom.2026.133622_bib0240","doi-asserted-by":"crossref","first-page":"2015","DOI":"10.1109\/TASLP.2022.3178204","article-title":"Multimodal sentiment analysis with two-phase multi-task learning","volume":"30","author":"Yang","year":"2022","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.neucom.2026.133622_bib0245","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"3722","article-title":"CubeMLP: an MLP-based model for multimodal sentiment analysis and depression estimation","author":"Sun","year":"2022"},{"key":"10.1016\/j.neucom.2026.133622_bib0250","series-title":"Findings of the Association for Computational Linguistics: ACL 2023","first-page":"13610","article-title":"ConKI: contrastive knowledge injection for multimodal sentiment analysis","author":"Yu","year":"2023"},{"key":"10.1016\/j.neucom.2026.133622_bib0255","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109259","article-title":"TETFN: a text enhanced transformer fusion network for multimodal sentiment analysis","volume":"136","author":"Wang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133622_bib0260","series-title":"2024 International Joint Conference on Neural Networks (IJCNN)","first-page":"1","article-title":"Shared and private information learning in multimodal sentiment analysis with deep modal alignment and self-supervised multi-task learning","author":"Lai","year":"2024"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226010192?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226010192?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:23:34Z","timestamp":1777577014000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226010192"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":52,"alternative-id":["S0925231226010192"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133622","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CMSA: Addressing semantic discrepancy and context dependency in multimodal sentiment analysis","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133622","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"133622"}}