{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:15:16Z","timestamp":1783095316422,"version":"3.54.6"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFC3308500"],"award-info":[{"award-number":["2024YFC3308500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004761","name":"Natural Science Foundation of Hainan Province","doi-asserted-by":"publisher","award":["725QN279"],"award-info":[{"award-number":["725QN279"]}],"id":[{"id":"10.13039\/501100004761","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62362019"],"award-info":[{"award-number":["62362019"]}],"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":[[2026,9]]},"DOI":"10.1016\/j.eswa.2026.132863","type":"journal-article","created":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T16:12:52Z","timestamp":1778861572000},"page":"132863","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Multimodal sentiment analysis with temporal semantics self-supervised multi-task learning and single-modality label generation"],"prefix":"10.1016","volume":"327","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9615-8226","authenticated-orcid":false,"given":"Meng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruixin","family":"Pu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0663-332X","authenticated-orcid":false,"given":"Pengfei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8668-1669","authenticated-orcid":false,"given":"Shudong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9434-1478","authenticated-orcid":false,"given":"Haoming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.eswa.2026.132863_bib0001","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.1109\/TAFFC.2025.3526592","article-title":"Multitask transformer for cross-corpus speech emotion recognition","volume":"16","author":"Ahn","year":"2025","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.eswa.2026.132863_bib0002","article-title":"CR-GAC: Cross-modal recombination via graph-attention collaborative optimization for multimodal sentiment analysis","author":"Chen","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"8","key":"10.1016\/j.eswa.2026.132863_bib0003","doi-asserted-by":"crossref","first-page":"6531","DOI":"10.1109\/TPAMI.2025.3560423","article-title":"Hadamard product in deep learning: Introduction, advances and challenges","volume":"47","author":"Chrysos","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"13s","key":"10.1016\/j.eswa.2026.132863_bib0004","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 Computing Surveys"},{"issue":"8","key":"10.1016\/j.eswa.2026.132863_bib0005","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1007\/s10462-025-11250-6","article-title":"Decoupling feature-driven and multimodal fusion attention for clothing-changing person re-identification","volume":"58","author":"Ding","year":"2025","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.eswa.2026.132863_bib0006","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1016\/j.inffus.2022.09.025","article-title":"Multimodal sentiment analysis: A systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions","volume":"91","author":"Gandhi","year":"2023","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132863_bib0007","article-title":"Towards robust sentiment analysis with multimodal interaction graph and hybrid contrastive learning","author":"Gong","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.132863_bib0008","doi-asserted-by":"crossref","unstructured":"Han, W., Chen, H., & Poria, S. (2021). Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. arXiv: 2109.00412.","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"10.1016\/j.eswa.2026.132863_bib0009","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.eswa.2026.132863_bib0010","doi-asserted-by":"crossref","first-page":"2304","DOI":"10.1109\/TMM.2024.3521836","article-title":"MULDEF: A model-agnostic debiasing framework for robust multimodal sentiment analysis","volume":"27","author":"Huan","year":"2025","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.132863_bib0011","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":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132863_bib0012","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"},{"issue":"1","key":"10.1016\/j.eswa.2026.132863_bib0013","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1109\/TAFFC.2024.3430045","article-title":"Diversity and balance: Multimodal sentiment analysis using multimodal-prefixed and cross-modal attention","volume":"16","author":"Li","year":"2024","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.eswa.2026.132863_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.126274","article-title":"Learning fine-grained representation with token-level alignment for multimodal sentiment analysis","volume":"269","author":"Li","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132863_bib0015","doi-asserted-by":"crossref","first-page":"2321","DOI":"10.1109\/TAFFC.2025.3559866","article-title":"Cormult: A semi-supervised modality correlation-aware multimodal transformer for sentiment analysis","volume":"16","author":"Li","year":"2025","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.eswa.2026.132863_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124236","article-title":"Hierarchical denoising representation disentanglement and dual-channel cross-modal-context interaction for multimodal sentiment analysis","volume":"252","author":"Li","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132863_bib0017","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1411","article-title":"Semi-IIN: Semi-supervised intra-inter modal interaction learning network for multimodal sentiment analysis","volume":"vol. 39","author":"Lin","year":"2025"},{"key":"10.1016\/j.eswa.2026.132863_bib0018","unstructured":"Liu, Z., Shen, Y., Lakshminarasimhan, V. B., Liang, P. P., Zadeh, A., & Morency, L.-P. (2018). Efficient low-rank multimodal fusion with modality-specific factors. arXiv: 1806.00064."},{"key":"10.1016\/j.eswa.2026.132863_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102747","article-title":"Multimodal dual perception fusion framework for multimodal affective analysis","volume":"115","author":"Lu","year":"2025","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132863_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.119721","article-title":"A fine-grained modal label-based multi-stage network for multimodal sentiment analysis","volume":"221","author":"Peng","year":"2023","journal-title":"Expert Systems with Applications"},{"issue":"9","key":"10.1016\/j.eswa.2026.132863_bib0021","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3652149","article-title":"A survey of cutting-edge multimodal sentiment analysis","volume":"56","author":"Singh","year":"2024","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.eswa.2026.132863_bib0022","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1016\/j.inffus.2022.10.031","article-title":"Modality-invariant temporal representation learning for multimodal sentiment classification","volume":"91","author":"Sun","year":"2023","journal-title":"Information Fusion"},{"issue":"3","key":"10.1016\/j.eswa.2026.132863_bib0023","doi-asserted-by":"crossref","first-page":"1606","DOI":"10.1109\/TAFFC.2025.3529732","article-title":"Multimodal sentiment analysis with mutual information-based disentangled representation learning","volume":"16","author":"Sun","year":"2025","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.eswa.2026.132863_bib0024","series-title":"Proceedings of the 57th annual meeting of the association for computational linguistics","first-page":"6558","article-title":"Multimodal transformer for unaligned multimodal language sequences","author":"Tsai","year":"2019"},{"key":"10.1016\/j.eswa.2026.132863_bib0025","unstructured":"Tsai, Y.-H. H., Liang, P. P., Zadeh, A., Morency, L.-P., & Salakhutdinov, R. (2018). Learning factorized multimodal representations. arXiv: 1806.06176."},{"key":"10.1016\/j.eswa.2026.132863_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.110777","article-title":"Covariance attention guidance mamba hashing for cross-modal retrieval","volume":"152","author":"Wang","year":"2025","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.132863_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109731","article-title":"Multimodal sentiment analysis based on multiple attention","volume":"140","author":"Wang","year":"2025","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"3","key":"10.1016\/j.eswa.2026.132863_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103675","article-title":"A cross modal hierarchical fusion multimodal sentiment analysis method based on multi-task learning","volume":"61","author":"Wang","year":"2024","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.eswa.2026.132863_bib0029","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"21180","article-title":"DLF: Disentangled-language-focused multimodal sentiment analysis","volume":"vol. 39","author":"Wang","year":"2025"},{"key":"10.1016\/j.eswa.2026.132863_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103058","article-title":"SSLMM: Semi-supervised learning with missing modalities for multimodal sentiment analysis","volume":"120","author":"Wang","year":"2025","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132863_bib0031","series-title":"Proceedings of the 2024 conference of the North American chapter of the association for computational linguistics: Human language technologies (volume 1: Long papers)","first-page":"3588","article-title":"Multimodal multi-loss fusion network for sentiment analysis","author":"Wu","year":"2024"},{"issue":"2","key":"10.1016\/j.eswa.2026.132863_bib0032","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1109\/TAFFC.2024.3456117","article-title":"Hierarchical knowledge stripping for multimodal sentiment analysis","volume":"16","author":"Xiong","year":"2024","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.eswa.2026.132863_bib0033","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.eswa.2026.132863_bib0034","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., & Morency, L.-P. (2017). Tensor fusion network for multimodal sentiment analysis. arXiv: 1707.07250.","DOI":"10.18653\/v1\/D17-1115"},{"key":"10.1016\/j.eswa.2026.132863_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2025.113078","article-title":"Multimodal sentiment analysis with text-augmented cross-modal feature interaction attention network","volume":"175","author":"Zhang","year":"2025","journal-title":"Applied Soft Computing"},{"key":"10.1016\/j.eswa.2026.132863_bib0036","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Yin, G., Liu, K., Liu, Y., & Yu, T. (2023). Learning language-guided adaptive hyper-modality representation for multimodal sentiment analysis. arXiv: 2310.05804.","DOI":"10.18653\/v1\/2023.emnlp-main.49"},{"key":"10.1016\/j.eswa.2026.132863_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113121","article-title":"Multilevel information compression and textual information enhancement for multimodal sentiment analysis","volume":"312","author":"Zhang","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.132863_bib0038","doi-asserted-by":"crossref","first-page":"1802","DOI":"10.1109\/TAFFC.2025.3539225","article-title":"SDRS: Sentiment-aware disentangled representation shifting for multimodal sentiment analysis","volume":"16","author":"Zhao","year":"2025","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.eswa.2026.132863_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102897","article-title":"Decoupled cross-attribute correlation network for multimodal sentiment analysis","volume":"117","author":"Zhao","year":"2025","journal-title":"Information Fusion"},{"issue":"10","key":"10.1016\/j.eswa.2026.132863_bib0040","doi-asserted-by":"crossref","first-page":"5886","DOI":"10.1109\/TFUZZ.2024.3434614","article-title":"A multimodal sentiment analysis method based on fuzzy attention fusion","volume":"32","author":"Zhi","year":"2024","journal-title":"IEEE Transactions on Fuzzy Systems"},{"key":"10.1016\/j.eswa.2026.132863_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102663","article-title":"Triple disentangled representation learning for multimodal affective analysis","volume":"114","author":"Zhou","year":"2025","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132863_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101958","article-title":"SKEAFN: Sentiment knowledge enhanced attention fusion network for multimodal sentiment analysis","volume":"100","author":"Zhu","year":"2023","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132863_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102787","article-title":"Multimodal sentiment analysis with unimodal label generation and modality decomposition","volume":"116","author":"Zhu","year":"2025","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132863_bib0044","doi-asserted-by":"crossref","first-page":"9044","DOI":"10.1109\/TMM.2025.3613116","article-title":"Multi-level contrastive learning for multimodal sentiment analysis","volume":"27","author":"Zhuang","year":"2025","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.132863_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125818","article-title":"TCMT: Target-oriented cross modal transformer for multimodal aspect-based sentiment analysis","volume":"264","author":"Zou","year":"2025","journal-title":"Expert Systems with Applications"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426017768?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426017768?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T15:16:06Z","timestamp":1783091766000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426017768"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":45,"alternative-id":["S0957417426017768"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132863","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multimodal sentiment analysis with temporal semantics self-supervised multi-task learning and single-modality label generation","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132863","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":"132863"}}