{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T04:01:25Z","timestamp":1785297685906,"version":"3.55.0"},"reference-count":39,"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":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":["U22A2025"],"award-info":[{"award-number":["U22A2025"]}],"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":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.132110","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T08:39:10Z","timestamp":1773909550000},"page":"132110","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["DGFN: Disentanglement-guided dynamic fusion network for multimodal sentiment analysis"],"prefix":"10.1016","volume":"319","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0811-5477","authenticated-orcid":false,"given":"Changxin","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2000-6683","authenticated-orcid":false,"given":"Hong","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6310-3843","authenticated-orcid":false,"given":"Lina","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132110_bib0001","first-page":"107795","article-title":"Vismin: Visual minimal-change understanding","volume":"37","author":"Awal","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"10.1016\/j.eswa.2026.132110_bib0002","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/s40846-019-00505-7","article-title":"Emotion recognition from multimodal physiological signals for emotion aware healthcare systems","volume":"40","author":"Ayata","year":"2020","journal-title":"Journal of Medical and Biological Engineering"},{"key":"10.1016\/j.eswa.2026.132110_bib0003","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4652","article-title":"M2fnet: Multi-modal fusion network for emotion recognition in conversation","author":"Chudasama","year":"2022"},{"key":"10.1016\/j.eswa.2026.132110_bib0004","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"14314","article-title":"Emoe: Modality-specific enhanced dynamic emotion experts","author":"Fang","year":"2025"},{"key":"10.1016\/j.eswa.2026.132110_bib0005","article-title":"Multimodal emotion recognition with deep learning: advancements, challenges, and future directions","volume":"105","author":"Geetha","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132110_bib0006","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"14375","article-title":"Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models","author":"Guan","year":"2024"},{"key":"10.1016\/j.eswa.2026.132110_bib0007","first-page":"10","article-title":"Current concerns and future directions of large language model chatGPT in medicine: A machine-learning-driven global-scale bibliometric analysis","author":"Guo","year":"2025","journal-title":"International Journal of Surgery"},{"key":"10.1016\/j.eswa.2026.132110_bib0008","series-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","author":"Gutmann","year":"2010"},{"key":"10.1016\/j.eswa.2026.132110_bib0009","series-title":"Proceedings of the 2021 international conference on multimodal interaction","first-page":"6","article-title":"Bi-bimodal modality fusion for correlation-controlled multimodal sentiment analysis","author":"Han","year":"2021"},{"key":"10.1016\/j.eswa.2026.132110_bib0010","doi-asserted-by":"crossref","unstructured":"Han, W., Chen, H., & Poria, S. (2021b). 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.2026.132110_bib0011","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.2026.132110_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.lindif.2023.102274","article-title":"ChatGPT for good? On opportunities and challenges of large language models for education","volume":"103","author":"Kasneci","year":"2023","journal-title":"Learning and Individual Differences"},{"key":"10.1016\/j.eswa.2026.132110_bib0013","series-title":"Interspeech","first-page":"4243","article-title":"Multimodal emotion recognition using cross-modal attention and 1d convolutional neural networks","author":"Krishna","year":"2020"},{"key":"10.1016\/j.eswa.2026.132110_bib0014","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6631","article-title":"Decoupled multimodal distilling for emotion recognition","author":"Li","year":"2023"},{"key":"10.1016\/j.eswa.2026.132110_bib0015","series-title":"Proceedings of the 29th international conference on computational linguistics","first-page":"7136","article-title":"Amoa: Global acoustic feature enhanced modal-order-aware network for multimodal sentiment analysis","author":"Li","year":"2022"},{"issue":"17-18","key":"10.1016\/j.eswa.2026.132110_bib0016","doi-asserted-by":"crossref","first-page":"8415","DOI":"10.1007\/s10489-024-05623-7","article-title":"A transformer-encoder-based multimodal multi-attention fusion network for sentiment analysis","volume":"54","author":"Liu","year":"2024","journal-title":"Applied Intelligence"},{"key":"10.1016\/j.eswa.2026.132110_bib0017","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.eswa.2026.132110_bib0018","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2554","article-title":"Progressive modality reinforcement for human multimodal emotion recognition from unaligned multimodal sequences","author":"Lv","year":"2021"},{"issue":"5","key":"10.1016\/j.eswa.2026.132110_bib0019","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3744746","article-title":"A comprehensive overview of large language models","volume":"16","author":"Naveed","year":"2025","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"10.1016\/j.eswa.2026.132110_bib0020","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2486","article-title":"A joint cross-attention model for audio-visual fusion in dimensional emotion recognition","author":"Praveen","year":"2022"},{"key":"10.1016\/j.eswa.2026.132110_bib0021","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.inffus.2018.06.004","article-title":"Ears: Emotion-aware recommender system based on hybrid information fusion","volume":"46","author":"Qian","year":"2019","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132110_bib0022","unstructured":"Qingyun, F., Dapeng, H., & Zhaokui, W. (2021). Cross-modality fusion transformer for multispectral object detection. arXiv: 2111.00273."},{"key":"10.1016\/j.eswa.2026.132110_bib0023","series-title":"Proceedings of the 58th annual meeting of the association for computational linguistics","first-page":"2359","article-title":"Integrating multimodal information in large pretrained transformers","author":"Rahman","year":"2020"},{"issue":"4","key":"10.1016\/j.eswa.2026.132110_bib0024","doi-asserted-by":"crossref","first-page":"2132","DOI":"10.1109\/TAFFC.2022.3188390","article-title":"Classifying emotions and engagement in online learning based on a single facial expression recognition neural network","volume":"13","author":"Savchenko","year":"2022","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.eswa.2026.132110_bib0025","unstructured":"THUIAR (2024). Mmsa: A multi-modal sentiment analysis toolkit. https:\/\/github.com\/thuiar\/MMSA. Accessed: 2024-08-10."},{"key":"10.1016\/j.eswa.2026.132110_bib0026","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"},{"key":"10.1016\/j.eswa.2026.132110_bib0027","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.2026.132110_bib0028","series-title":"Proceedings of grand challenge and workshop on human multimodal language (challenge-HML)","first-page":"64","article-title":"DNN multimodal fusion techniques for predicting video sentiment","author":"Williams","year":"2018"},{"key":"10.1016\/j.eswa.2026.132110_bib0029","series-title":"Grand challenge and workshop on human multimodal language","first-page":"11","article-title":"Recognizing emotions in video using multimodal DNN feature fusion","author":"Williams","year":"2018"},{"issue":"4","key":"10.1016\/j.eswa.2026.132110_bib0030","doi-asserted-by":"crossref","first-page":"2974","DOI":"10.1109\/TII.2020.3005405","article-title":"Social image sentiment analysis by exploiting multimodal content and heterogeneous relations","volume":"17","author":"Xu","year":"2020","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"10","key":"10.1016\/j.eswa.2026.132110_bib0031","doi-asserted-by":"crossref","first-page":"12113","DOI":"10.1109\/TPAMI.2023.3275156","article-title":"Multimodal learning with transformers: A survey","volume":"45","author":"Xu","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"10.1016\/j.eswa.2026.132110_bib0032","doi-asserted-by":"crossref","DOI":"10.1080\/08839514.2021.2000688","article-title":"Multimodal sentiment analysis using multi-tensor fusion network with cross-modal modeling","volume":"36","author":"Yan","year":"2022","journal-title":"Applied Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.132110_bib0033","series-title":"Proceedings of the 30th ACM international conference on multimedia","first-page":"1642","article-title":"Disentangled representation learning for multimodal emotion recognition","author":"Yang","year":"2022"},{"key":"10.1016\/j.eswa.2026.132110_bib0034","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.2026.132110_bib0035","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.2026.132110_bib0036","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.eswa.2026.132110_bib0037","series-title":"Proceedings of the 56th annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"2236","article-title":"Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph","author":"Zadeh","year":"2018"},{"key":"10.1016\/j.eswa.2026.132110_bib0038","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.2026.132110_bib0039","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1016\/j.inffus.2023.02.028","article-title":"Multimodal sentiment analysis based on fusion methods: A survey","volume":"95","author":"Zhu","year":"2023","journal-title":"Information Fusion"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426010237?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426010237?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T02:40:31Z","timestamp":1780972831000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426010237"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":39,"alternative-id":["S0957417426010237"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132110","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DGFN: Disentanglement-guided dynamic fusion network for multimodal sentiment analysis","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132110","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":"132110"}}