{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T02:34:08Z","timestamp":1785551648798,"version":"3.56.0"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100006683","name":"XJTLU","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006683","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702462"],"award-info":[{"award-number":["61702462"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006407","name":"Natural Science Foundation of Henan Province","doi-asserted-by":"publisher","award":["242300421220"],"award-info":[{"award-number":["242300421220"]}],"id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neunet.2026.108995","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T15:07:23Z","timestamp":1776352043000},"page":"108995","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["A text-guided cross-hierarchical fusion and multi-task learning framework for multimodal sentiment analysis"],"prefix":"10.1016","volume":"202","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3621-2142","authenticated-orcid":false,"given":"Minghui","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6877-3937","authenticated-orcid":false,"given":"Yushan","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4028-2287","authenticated-orcid":false,"given":"Nan","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuhe","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6896-0572","authenticated-orcid":false,"given":"Di","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1743-0516","authenticated-orcid":false,"given":"Zhiyang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4536-6220","authenticated-orcid":false,"given":"Yuanping","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0524-5926","authenticated-orcid":false,"given":"Zhijie","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108995_bib0001","series-title":"Proceedings of NAACL-HLT","first-page":"370","article-title":"Multi-task learning for multi-modal emotion recognition and sentiment analysis","author":"Akhtar","year":"2019"},{"key":"10.1016\/j.neunet.2026.108995_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2023.110494","article-title":"Attention-based multimodal sentiment analysis and emotion recognition using deep neural networks","volume":"144","author":"Aslam","year":"2023","journal-title":"Applied Soft Computing"},{"key":"10.1016\/j.neunet.2026.108995_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijhcs.2023.103046","article-title":"Towards interactive customization of multimodal embedded navigation systems for visually impaired people","volume":"176","author":"Dourado","year":"2023","journal-title":"International Journal of Human-Computer Studies"},{"key":"10.1016\/j.neunet.2026.108995_bib0004","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.1961","article-title":"Detecting cyberbullying using deep learning techniques: A pre-trained glove and focal loss technique","volume":"10","author":"El Koshiry","year":"2024","journal-title":"PeerJ Computer Science"},{"key":"10.1016\/j.neunet.2026.108995_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijhcs.2025.103486","article-title":"Emoland: Utilizing narrative animations, multilevel games, and affective computing to foster emotional development in children with autism spectrum disorder","volume":"199","author":"Fan","year":"2025","journal-title":"International Journal of Human-Computer Studies"},{"key":"10.1016\/j.neunet.2026.108995_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127201","article-title":"Hybrid cross-modal interaction learning for multimodal sentiment analysis","volume":"571","author":"Fu","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.108995_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111982","article-title":"Video multimodal sentiment analysis using cross-modal feature translation and dynamical propagation","author":"Gan","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.108995_bib0008","series-title":"Proceedings of the 2021 conference on empirical methods in natural language processing","first-page":"9180","article-title":"Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis","author":"Han","year":"2021"},{"key":"10.1016\/j.neunet.2026.108995_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.neunet.2026.108995_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129532","article-title":"Text-guided multi-level interaction and multi-scale spatial-memory fusion for multimodal sentiment analysis","volume":"626","author":"He","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.108995_bib0011","doi-asserted-by":"crossref","first-page":"3169","DOI":"10.1109\/TAFFC.2025.3580779","article-title":"Scale-selectable global information and discrepancy learning network for multimodal sentiment analysis","volume":"16","author":"He","year":"2025","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.neunet.2026.108995_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijhcs.2024.103440","article-title":"Different adaptation error types in affective computing have different effects on user experience: A wizard-of-oz study","volume":"196","author":"Hossain","year":"2025","journal-title":"International Journal of Human-Computer Studies"},{"key":"10.1016\/j.neunet.2026.108995_bib0013","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.neunet.2026.108995_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111346","article-title":"Tmbl: Transformer-based multimodal binding learning model for multimodal sentiment analysis","volume":"285","author":"Huang","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.108995_bib0015","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.procs.2021.05.080","article-title":"Automatic detection of cyberbullying and abusive language in arabic content on social networks: A survey","volume":"189","author":"Khairy","year":"2021","journal-title":"Procedia Computer Science"},{"issue":"3","key":"10.1016\/j.neunet.2026.108995_bib0016","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1007\/s00521-023-09084-w","article-title":"The effect of rebalancing techniques on the classification performance in cyberbullying datasets","volume":"36","author":"Khairy","year":"2024","journal-title":"Neural Computing and Applications"},{"key":"10.1016\/j.neunet.2026.108995_bib0017","series-title":"Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)","article-title":"Convolutional neural networks for sentence classification","author":"Kim","year":"2014"},{"key":"10.1016\/j.neunet.2026.108995_bib0018","series-title":"International conference on intelligent systems design and applications","first-page":"464","article-title":"Image sentiment analysis using convolutional neural network","author":"Kumar","year":"2017"},{"key":"10.1016\/j.neunet.2026.108995_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijhcs.2022.102916","article-title":"Hmmcf: A human-computer collaboration algorithm based on multimodal intention of reverse active fusion","volume":"169","author":"Lang","year":"2023","journal-title":"International Journal of Human-Computer Studies"},{"key":"10.1016\/j.neunet.2026.108995_sbref0020","article-title":"Learning fine-grained representation with token-level alignment for multimodal sentiment analysis","author":"Li","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.108995_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130810","article-title":"Emoverse: Enhancing multimodal large language models for affective computing via multitask learning","volume":"650","author":"Li","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.108995_bib0022","article-title":"Learning fine-grained representation with token-level alignment for multimodal sentiment analysis","author":"Li","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.108995_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101891","article-title":"Multi-level correlation mining framework with self-supervised label generation for multimodal sentiment analysis","volume":"99","author":"Li","year":"2023","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.108995_sbref0024","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.neunet.2026.108995_bib0025","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yuan, Z., Mao, H., Liang, Z., Yang, W., Qiu, Y., Cheng, T., Li, X., Xu, H., & Gao, K. (2022). Make acoustic and visual cues matter: CH-SIMS v2.0 dataset and AV-mixup consistent module.","DOI":"10.1145\/3536221.3556630"},{"key":"10.1016\/j.neunet.2026.108995_sbref0026","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.neunet.2026.108995_bib0027","series-title":"2018\u202fIEEE\/WIC\/ACM international conference on web intelligence (WI)","first-page":"684","article-title":"Image sentiment analysis using deep learning","author":"Mittal","year":"2018"},{"issue":"1","key":"10.1016\/j.neunet.2026.108995_bib0028","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-023-44113-7","article-title":"Quantum computing and machine learning for arabic language sentiment classification in social media","volume":"13","author":"Omar","year":"2023","journal-title":"Scientific Reports"},{"key":"10.1016\/j.neunet.2026.108995_bib0029","series-title":"The international conference on artificial intelligence and computer vision","first-page":"247","article-title":"Comparative performance of machine learning and deep learning algorithms for Arabic hate speech detection in osns","author":"Omar","year":"2020"},{"key":"10.1016\/j.neunet.2026.108995_bib0030","series-title":"ICASSP 2021-2021 IEEE international conference on acoustics, speech and signal processing (icassp)","first-page":"3020","article-title":"Efficient speech emotion recognition using multi-scale cnn and attention","author":"Peng","year":"2021"},{"key":"10.1016\/j.neunet.2026.108995_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111149","article-title":"Co-space representation interaction network for multimodal sentiment analysis","volume":"283","author":"Shi","year":"2024","journal-title":"Knowledge-Based Systems"},{"issue":"2","key":"10.1016\/j.neunet.2026.108995_bib0032","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1007\/s12369-009-0012-8","article-title":"How quickly should a communication robot respond? Delaying strategies and habituation effects","volume":"1","author":"Shiwa","year":"2009","journal-title":"International Journal of Social Robotics"},{"key":"10.1016\/j.neunet.2026.108995_bib0033","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"26963","article-title":"Contextual augmented global contrast for multimodal intent recognition","author":"Sun","year":"2024"},{"key":"10.1016\/j.neunet.2026.108995_bib0034","series-title":"Proceedings of the 52nd annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"1555","article-title":"Learning sentiment-specific word embedding for Twitter sentiment classification","author":"Tang","year":"2014"},{"issue":"1","key":"10.1016\/j.neunet.2026.108995_bib0035","doi-asserted-by":"crossref","first-page":"4095","DOI":"10.1109\/TCE.2024.3357480","article-title":"Multi-view interactive representations for multimodal sentiment analysis","volume":"70","author":"Tang","year":"2024","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"10.1016\/j.neunet.2026.108995_bib0036","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.neunet.2026.108995_bib0037","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108995_sbref0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129163","article-title":"Transformer-based correlation mining network with self-supervised label generation for multimodal sentiment analysis","volume":"618","author":"Wang","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.108995_bib0039","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 Recognition"},{"issue":"1","key":"10.1016\/j.neunet.2026.108995_bib0040","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1007\/s12559-022-10073-9","article-title":"Tedt: Transformer-based encoding\u2013decoding translation network for multimodal sentiment analysis","volume":"15","author":"Wang","year":"2023","journal-title":"Cognitive Computation"},{"key":"10.1016\/j.neunet.2026.108995_bib0041","first-page":"1","article-title":"A method for multimodal sentiment analysis: Adaptive interaction and multi-scale fusion","author":"Wang","year":"2025","journal-title":"Journal of Intelligent Information Systems"},{"key":"10.1016\/j.neunet.2026.108995_bib0042","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"},{"key":"10.1016\/j.neunet.2026.108995_bib0043","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.ins.2023.01.116","article-title":"Learning speaker-independent multimodal representation for sentiment analysis","volume":"628","author":"Wang","year":"2023","journal-title":"Information Sciences"},{"key":"10.1016\/j.neunet.2026.108995_bib0044","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","article-title":"Eca-net: Efficient channel attention for deep convolutional neural networks","author":"Wang","year":"2020"},{"key":"10.1016\/j.neunet.2026.108995_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.107676","article-title":"Video sentiment analysis with bimodal information-augmented multi-head attention","volume":"235","author":"Wu","year":"2022","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.108995_bib0046","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126649","article-title":"A multimodal fusion emotion recognition method based on multitask learning and attention mechanism","volume":"556","author":"Xie","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.108995_bib0047","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103230","article-title":"Ccin-sa: Composite cross modal interaction network with attention enhancement for multimodal sentiment analysis","author":"Yang","year":"2025","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.108995_bib0048","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111136","article-title":"Vlp2msa: Expanding vision-language pre-training to multimodal sentiment analysis","volume":"283","author":"Yi","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.108995_bib0049","series-title":"Proceedings of the 58th annual meeting of the association for computational linguistics","first-page":"3718","article-title":"Ch-sims: A Chinese multimodal sentiment analysis dataset with fine-grained annotation of modality","author":"Yu","year":"2020"},{"key":"10.1016\/j.neunet.2026.108995_bib0050","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.neunet.2026.108995_bib0051","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.neunet.2026.108995_bib0052","unstructured":"Zadeh, A., Zellers, R., Pincus, E., & Morency, L.-P. (2016). Mosi: Multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. arXiv: 1606.06259."},{"key":"10.1016\/j.neunet.2026.108995_bib0053","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.neunet.2026.108995_bib0054","series-title":"Proceedings of the 2023 conference on empirical methods in natural language processing","first-page":"756","article-title":"Learning language-guided adaptive hyper-modality representation for multimodal sentiment analysis","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.108995_bib0055","series-title":"2018 Asia-Pacific signal and information processing association annual summit and conference (APSIPA ASC)","first-page":"1771","article-title":"Attention based fully convolutional network for speech emotion recognition","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neunet.2026.108995_bib0056","article-title":"A multimodal sentiment analysis approach based on multiview cross-modal fusion","author":"Zhi","year":"2025","journal-title":"IEEE Transactions on Computational Social Systems"},{"key":"10.1016\/j.neunet.2026.108995_bib0057","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.neunet.2026.108995_bib0058","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.3033","article-title":"Local-global multi-scale attention network for medical image segmentation","volume":"11","author":"Zhu","year":"2025","journal-title":"PeerJ Computer Science"},{"key":"10.1016\/j.neunet.2026.108995_bib0059","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113249","article-title":"Text-guided deep correlation mining and self-learning feature fusion framework for multimodal sentiment analysis","volume":"315","author":"Zhu","year":"2025","journal-title":"Knowledge-Based Systems"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004569?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004569?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:19:31Z","timestamp":1784200771000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026004569"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":59,"alternative-id":["S0893608026004569"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108995","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A text-guided cross-hierarchical fusion and multi-task learning framework for multimodal sentiment analysis","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108995","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":"108995"}}