{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T10:21:39Z","timestamp":1779099699725,"version":"3.51.4"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T00:00:00Z","timestamp":1724371200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T00:00:00Z","timestamp":1724371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100017338","name":"Key Program of NSFC-Tongyong Union Foundation","doi-asserted-by":"publisher","award":["No.62276196"],"award-info":[{"award-number":["No.62276196"]}],"id":[{"id":"10.13039\/100017338","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017338","name":"Key Program of NSFC-Tongyong Union Foundation","doi-asserted-by":"publisher","award":["No.62276196"],"award-info":[{"award-number":["No.62276196"]}],"id":[{"id":"10.13039\/100017338","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s10044-024-01320-w","type":"journal-article","created":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T19:02:30Z","timestamp":1724439750000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["CSMF-SPC: Multimodal Sentiment Analysis Model with Effective Context Semantic Modality Fusion and Sentiment Polarity Correction"],"prefix":"10.1007","volume":"27","author":[{"given":"Yuqiang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxuan","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,23]]},"reference":[{"issue":"7","key":"1320_CR1","first-page":"1165","volume":"15","author":"L Jiming","year":"2021","unstructured":"Jiming L, Peixiang Z, Ying L, Weidong Z, Jie F (2021) Summary of multi-modal sentiment analysis technology. J Front Comput Sci Technol 15(7):1165","journal-title":"J Front Comput Sci Technol"},{"issue":"5","key":"1320_CR2","first-page":"426","volume":"33","author":"Y Zhang","year":"2020","unstructured":"Zhang Y, Rong L, Song D, Zhang P (2020) A survey on multimodal sentiment analysis. Pattern Recognit Artif Intell 33(5):426\u2013438","journal-title":"Pattern Recognit Artif Intell"},{"key":"1320_CR3","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1016\/j.inffus.2022.09.025","volume":"91","author":"A Gandhi","year":"2023","unstructured":"Gandhi A, Adhvaryu K, Poria S, Cambria E, Hussain A (2023) Multimodal sentiment analysis: a systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions. Inf Fusion 91:424\u2013444","journal-title":"Inf Fusion"},{"key":"1320_CR4","doi-asserted-by":"crossref","unstructured":"Melville P, Gryc W, Lawrence RD (2009) Sentiment analysis of blogs by combining lexical knowledge with text classification. In: Proceedings of the 15th ACM SIGKDD international conference on knowledge discovery and data mining, pp 1275\u20131284","DOI":"10.1145\/1557019.1557156"},{"key":"1320_CR5","doi-asserted-by":"crossref","unstructured":"Tumasjan A, Sprenger T, Sandner P, Welpe I (2010) Predicting elections with twitter: what 140 characters reveal about political sentiment. In: Proceedings of the international AAAI conference on web and social media, vol. 4, pp 178\u2013185","DOI":"10.1609\/icwsm.v4i1.14009"},{"key":"1320_CR6","doi-asserted-by":"crossref","unstructured":"Tsai Y-HH, Bai S, Liang PP, Kolter JZ, Morency L-P, Salakhutdinov R (2019) Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the conference. Association for computational linguistics. Meeting, vol. 2019, p 6558. NIH Public Access","DOI":"10.18653\/v1\/P19-1656"},{"key":"1320_CR7","doi-asserted-by":"crossref","unstructured":"Hazarika D, Zimmermann R, Poria S (2020) Misa: modality-invariant and-specific representations for multimodal sentiment analysis. In: Proceedings of the 28th ACM international conference on multimedia, pp 1122\u20131131","DOI":"10.1145\/3394171.3413678"},{"key":"1320_CR8","doi-asserted-by":"crossref","unstructured":"Yu W, Xu H, Yuan Z, Wu J (2021) Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. In: Proceedings of the AAAI conference on artificial intelligence, vol. 35, pp 10790\u201310797","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"1320_CR9","doi-asserted-by":"crossref","unstructured":"Han W, Chen H, Poria S (2021) Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. In: Proceedings of the 2021 conference on empirical methods in natural language processing, pp 9180\u20139192","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"1320_CR10","doi-asserted-by":"crossref","unstructured":"Ghosal D, Majumder N, Poria S, Chhaya N, Gelbukh A (2019) Dialoguegcn: a graph convolutional neural network for emotion recognition in conversation. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 154\u2013164","DOI":"10.18653\/v1\/D19-1015"},{"key":"1320_CR11","doi-asserted-by":"crossref","unstructured":"Chen M, Wang S, Liang PP, Baltru\u0161aitis T, Zadeh A, Morency L-P (2017) Multimodal sentiment analysis with word-level fusion and reinforcement learning. In: Proceedings of the 19th ACM international conference on multimodal interaction, pp 163\u2013171","DOI":"10.1145\/3136755.3136801"},{"key":"1320_CR12","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.neucom.2021.09.041","volume":"467","author":"B Yang","year":"2022","unstructured":"Yang B, Shao B, Wu L, Lin X (2022) Multimodal sentiment analysis with unidirectional modality translation. Neurocomputing 467:130\u2013137","journal-title":"Neurocomputing"},{"key":"1320_CR13","doi-asserted-by":"crossref","unstructured":"Wang Z, Wan Z, Wan X (2020) Transmodality: an end2end fusion method with transformer for multimodal sentiment analysis. In: Proceedings of the web conference 2020, pp 2514\u20132520","DOI":"10.1145\/3366423.3380000"},{"key":"1320_CR14","doi-asserted-by":"crossref","unstructured":"Tsai Y-HH, Ma, MQ, Yang M, Salakhutdinov R, Morency L-P (2020) Multimodal routing: improving local and global interpretability of multimodal language analysis. In: Proceedings of the conference on empirical methods in natural language processing. Conference on empirical methods in natural language processing, vol. 2020, pp 1823\u20131833","DOI":"10.18653\/v1\/2020.emnlp-main.143"},{"key":"1320_CR15","doi-asserted-by":"publisher","first-page":"2015","DOI":"10.1109\/TASLP.2022.3178204","volume":"30","author":"B Yang","year":"2022","unstructured":"Yang B, Wu L, Zhu J, Shao B, Lin X, Liu T-Y (2022) Multimodal sentiment analysis with two-phase multi-task learning. IEEE\/ACM Trans Audio Speech Lang Process 30:2015\u20132024","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"1320_CR16","unstructured":"Ma L, Yao Y, Liang T, Liu T (2022) Multi-scale cooperative multimodal transformers for multimodal sentiment analysis in videos. arXiv preprint arXiv:2206.07981"},{"key":"1320_CR17","doi-asserted-by":"crossref","unstructured":"Liu Z, Shen Y, Lakshminarasimhan VB, Liang PP, Zadeh AB, Morency L-P (2018) Efficient low-rank multimodal fusion with modality-specific factors. In: Proceedings of the 56th annual meeting of the association for computational linguistics (Volume 1: long papers), pp 2247\u20132256","DOI":"10.18653\/v1\/P18-1209"},{"key":"1320_CR18","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1725\u20131732","DOI":"10.1109\/CVPR.2014.223"},{"key":"1320_CR19","doi-asserted-by":"publisher","first-page":"5929","DOI":"10.1007\/s10462-020-09838-1","volume":"53","author":"G Van Houdt","year":"2020","unstructured":"Van Houdt G, Mosquera C, N\u00e1poles G (2020) A review on the long short-term memory model. Artif Intell Rev 53:5929\u20135955","journal-title":"Artif Intell Rev"},{"key":"1320_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107657","volume":"235","author":"IC Kaadoud","year":"2022","unstructured":"Kaadoud IC, Rougier NP, Alexandre F (2022) Knowledge extraction from the learning of sequences in a long short term memory (lstm) architecture. Knowl-Based Syst 235:107657","journal-title":"Knowl-Based Syst"},{"key":"1320_CR21","doi-asserted-by":"publisher","first-page":"4121","DOI":"10.1109\/TMM.2022.3171679","volume":"25","author":"S Mai","year":"2022","unstructured":"Mai S, Zeng Y, Hu H (2022) Multimodal information bottleneck: learning minimal sufficient unimodal and multimodal representations. IEEE Trans Multimed 25:4121","journal-title":"IEEE Trans Multimed"},{"key":"1320_CR22","doi-asserted-by":"crossref","unstructured":"Zadeh A, Chen M, Poria S, Cambria E, Morency L-P (2017) Tensor fusion network for multimodal sentiment analysis. In: Proceedings of the 2017 conference on empirical methods in natural language processing, pp 1103\u20131114","DOI":"10.18653\/v1\/D17-1115"},{"key":"1320_CR23","doi-asserted-by":"crossref","unstructured":"Lv F, Chen X, Huang Y, Duan L, Lin G (2021) Progressive modality reinforcement for human multimodal emotion recognition from unaligned multimodal sequences. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2554\u20132562","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"1320_CR24","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1109\/TAFFC.2023.3274829","volume":"15","author":"L Sun","year":"2023","unstructured":"Sun L, Lian Z, Liu B, Tao J (2023) Efficient multimodal transformer with dual-level feature restoration for robust multimodal sentiment analysis. IEEE Trans Affect Comput 15:309","journal-title":"IEEE Trans Affect Comput"},{"key":"1320_CR25","doi-asserted-by":"crossref","unstructured":"Yuan Z, Li W, Xu H, Yu W (2021) Transformer-based feature reconstruction network for robust multimodal sentiment analysis. In: Proceedings of the 29th ACM international conference on multimedia, pp 4400\u20134407","DOI":"10.1145\/3474085.3475585"},{"issue":"2","key":"1320_CR26","doi-asserted-by":"publisher","first-page":"103229","DOI":"10.1016\/j.ipm.2022.103229","volume":"60","author":"H Lin","year":"2023","unstructured":"Lin H, Zhang P, Ling J, Yang Z, Lee LK, Liu W (2023) Ps-mixer: a polar-vector and strength-vector mixer model for multimodal sentiment analysis. Inf Process Manag 60(2):103229\u2013103245","journal-title":"Inf Process Manag"},{"key":"1320_CR27","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"issue":"6","key":"1320_CR28","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MIS.2016.94","volume":"31","author":"A Zadeh","year":"2016","unstructured":"Zadeh A, Zellers R, Pincus E, Morency L-P (2016) Multimodal sentiment intensity analysis in videos: facial gestures and verbal messages. IEEE Intell Syst 31(6):82\u201388","journal-title":"IEEE Intell Syst"},{"key":"1320_CR29","doi-asserted-by":"crossref","unstructured":"Zadeh AB, Liang PP, Poria S, Cambria E, Morency L-P (2018) Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph. In: Proceedings of the 56th annual meeting of the association for computational linguistics (Volume 1: long papers), pp 2236\u20132246","DOI":"10.18653\/v1\/P18-1208"},{"issue":"5","key":"1320_CR30","doi-asserted-by":"publisher","first-page":"3878","DOI":"10.1121\/1.2935783","volume":"123","author":"J Yuan","year":"2008","unstructured":"Yuan J, Liberman M et al (2008) Speaker identification on the scotus corpus. J Acoust Soc Am 123(5):3878","journal-title":"J Acoust Soc Am"},{"key":"1320_CR31","doi-asserted-by":"crossref","unstructured":"Degottex G, Kane J, Drugman T, Raitio T, Scherer S (2014) Covarep-a collaborative voice analysis repository for speech technologies. In: 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 960\u2013964. IEEE","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"1320_CR32","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.inffus.2022.07.006","volume":"88","author":"F Zhang","year":"2022","unstructured":"Zhang F, Li X-C, Lim CP, Hua Q, Dong C-R, Zhai J-H (2022) Deep emotional arousal network for multimodal sentiment analysis and emotion recognition. Inf Fusion 88:296\u2013304","journal-title":"Inf Fusion"},{"key":"1320_CR33","doi-asserted-by":"crossref","unstructured":"Ma Y, Ma B (2022) Multimodal sentiment analysis on unaligned sequences via holographic embedding. In: ICASSP 2022-2022 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 8547\u20138551. IEEE","DOI":"10.1109\/ICASSP43922.2022.9747646"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-024-01320-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-024-01320-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-024-01320-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T18:18:05Z","timestamp":1726165085000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-024-01320-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,23]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["1320"],"URL":"https:\/\/doi.org\/10.1007\/s10044-024-01320-w","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,23]]},"assertion":[{"value":"15 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-fi-nancial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"104"}}