{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T18:01:24Z","timestamp":1771264884510,"version":"3.50.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"23","license":[{"start":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T00:00:00Z","timestamp":1704931200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T00:00:00Z","timestamp":1704931200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-18032-8","type":"journal-article","created":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T05:01:31Z","timestamp":1704949291000},"page":"63291-63308","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Low-rank tensor fusion and self-supervised multi-task multimodal sentiment analysis"],"prefix":"10.1007","volume":"83","author":[{"given":"Xinmeng","family":"Miao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8684-5802","authenticated-orcid":false,"given":"Xuguang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Haoran","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,11]]},"reference":[{"key":"18032_CR1","unstructured":"Tawunrat C, Jeremy E (2015) Chapter information science and applications, simple approaches of sentiment analysis via ensemble learning, vol 339 of the series lecture notes in electrical engineering, DISCIPLINES Computer Science, Engineering SUBDISCIPLINESAI. Information Systems and Applications- Computational Intelligence and Complexity"},{"issue":"2","key":"18032_CR2","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2018","unstructured":"Baltru\u0161aitis T, Ahuja C, Morency L-P (2018) Multimodal machine learning: a survey and taxonomy. IEEE Trans Pattern Anal Mach Intell 41(2):423\u2013443","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"18032_CR3","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1016\/j.inffus.2022.09.025","volume":"91","author":"A Gandhi","year":"2022","unstructured":"Gandhi A, Adhvaryu K, Poria S, Cambria E, Hussain A (2022) Multimodal sentiment analysis: a systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions. Information Fusion 91:424\u2013444","journal-title":"Information Fusion"},{"key":"18032_CR4","doi-asserted-by":"publisher","first-page":"2131","DOI":"10.1007\/s13042-017-0757-6","volume":"10","author":"Y Cai","year":"2019","unstructured":"Cai Y, Yang K, Huang D, Zhou Z, Lei X, Xie H, Wong TL (2019) A hybrid model for opinion mining based on domain sentiment dictionary. International Journal of Machine Learning and Cybernetics 10:2131\u20132142","journal-title":"International Journal of Machine Learning and Cybernetics"},{"issue":"3","key":"18032_CR5","doi-asserted-by":"publisher","first-page":"7004","DOI":"10.2196\/publichealth.7004","volume":"3","author":"M Roccetti","year":"2017","unstructured":"Roccetti M, Marfia G, Salomoni P, Prandi C, Zagari RM, Kengni FLG, Bazzoli F, Montagnani M (2017) Attitudes of Crohn\u2019s disease patients: infodemiology case study and sentiment analysis of Facebook and Twitter posts. JMIR Public Health Surveill 3(3):7004","journal-title":"JMIR Public Health Surveill"},{"key":"18032_CR6","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1007\/s11280-013-0221-9","volume":"17","author":"Y Rao","year":"2014","unstructured":"Rao Y, Lei J, Wenyin L, Li Q, Chen M (2014) Building emotional dictionary for sentiment analysis of online news. World Wide Web 17:723\u2013742","journal-title":"World Wide Web"},{"key":"18032_CR7","doi-asserted-by":"crossref","unstructured":"Kamal A, Abulaish M (2013) Statistical features identification for sentiment analysis using machine learning techniques. In: 2013 International symposium on computational and business intelligence, pp 178\u2013181 IEEE","DOI":"10.1109\/ISCBI.2013.43"},{"key":"18032_CR8","unstructured":"Vijayaraghavan S, Basu D (2020) Sentiment analysis in drug reviews using supervised machine learning algorithms. arXiv:2003.11643"},{"key":"18032_CR9","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85\u2013117","journal-title":"Neural Netw"},{"issue":"14","key":"18032_CR10","doi-asserted-by":"publisher","first-page":"1959046","DOI":"10.1142\/S0218001419590468","volume":"33","author":"Y Xing","year":"2019","unstructured":"Xing Y, Xiao C, Wu Y, Ding Z (2019) A convolutional neural network for aspect-level sentiment classification. Int J Pattern Recogn Artif Intell 33(14):1959046","journal-title":"Int J Pattern Recogn Artif Intell"},{"key":"18032_CR11","doi-asserted-by":"crossref","unstructured":"Li R, Wu Z, Jia J, Bu Y, Zhao S, Meng H (2019) Towards discriminative representation learning for speech emotion recognition. In: IJCAI, pp 5060\u20135066","DOI":"10.24963\/ijcai.2019\/703"},{"key":"18032_CR12","doi-asserted-by":"crossref","unstructured":"Savargiv M, Bastanfard A (2013) Text material design for fuzzy emotional speech corpus based on persian semantic and structure. In: 2013 International conference on fuzzy theory and its applications (iFUZZY), pp 380\u2013384. IEEE","DOI":"10.1109\/iFuzzy.2013.6825469"},{"key":"18032_CR13","doi-asserted-by":"crossref","unstructured":"Gandhi A, Adhvaryu K, Khanduja V (2021) Multimodal sentiment analysis: review, application domains and future directions. In: 2021 IEEE Pune section international conference (PuneCon), pp 1\u20135. IEEE","DOI":"10.1109\/PuneCon52575.2021.9686504"},{"key":"18032_CR14","doi-asserted-by":"crossref","unstructured":"Demotte P, Wijegunarathna K, Meedeniya D, Perera I (2021) Enhanced sentiment extraction architecture for social media content analysis using capsule networks. Multimedia Tools Appl 1\u201326","DOI":"10.1007\/s11042-021-11471-1"},{"key":"18032_CR15","unstructured":"Poria S, Hazarika D, Majumder N, Mihalcea R (2020) Beneath the tip of the iceberg: current challenges and new directions in sentiment analysis research. IEEE Trans Affect Comput"},{"key":"18032_CR16","doi-asserted-by":"publisher","first-page":"6871","DOI":"10.1007\/s11042-020-10037-x","volume":"80","author":"JV Tembhurne","year":"2021","unstructured":"Tembhurne JV, Diwan T (2021) Sentiment analysis in textual, visual and multimodal inputs using recurrent neural networks. Multimedia Tools Appl 80:6871\u20136910","journal-title":"Multimedia Tools Appl"},{"key":"18032_CR17","doi-asserted-by":"publisher","first-page":"63373","DOI":"10.1109\/ACCESS.2019.2916887","volume":"7","author":"W Guo","year":"2019","unstructured":"Guo W, Wang J, Wang S (2019) Deep multimodal representation learning: a survey. IEEE Access 7:63373\u201363394","journal-title":"IEEE Access"},{"key":"18032_CR18","doi-asserted-by":"crossref","unstructured":"Cao R, Ye C, Zhou H (2021) Multimodel sentiment analysis with self-attention. In: Proceedings of the future technologies conference (FTC) 2020, vol 1, pp 16\u201326. Springer","DOI":"10.1007\/978-3-030-63128-4_2"},{"key":"18032_CR19","doi-asserted-by":"crossref","unstructured":"Zadeh A, Chen M, Poria S, Cambria E, Morency L\u2013P (2017) Tensor fusion network for multimodal sentiment analysis. arXiv:1707.07250","DOI":"10.18653\/v1\/D17-1115"},{"key":"18032_CR20","doi-asserted-by":"crossref","unstructured":"Yu W, Xu H, Meng F, Zhu Y, Ma Y, Wu J, Zou J, Yang K (2020) Ch-sims: a Chinese multimodal sentiment analysis dataset with fine\u2013grained annotation of modality. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 3718\u20133727","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"18032_CR21","doi-asserted-by":"publisher","first-page":"10790","DOI":"10.1609\/aaai.v35i12.17289","volume":"35","author":"W Yu","year":"2021","unstructured":"Yu W, Xu H, Yuan Z, Wu J (2021) Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. Proceedings of the AAAI Conference on Artificial Intelligence 35:10790\u201310797","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"18032_CR22","unstructured":"Misra D (2019) Mish: a self regularized non-monotonic activation function. arXiv:1908.08681"},{"key":"18032_CR23","unstructured":"Misra D (2019) Mish: a self regularized non-monotonic activation function. arXiv:1908.08681"},{"key":"18032_CR24","doi-asserted-by":"crossref","unstructured":"Morency LP, Mihalcea R, Doshi P (2011) Towards multimodal sentiment analysis: harvesting opinions from the web. In: Proceedings of the 13th International conference on multimodal interfaces, pp 169\u2013176","DOI":"10.1145\/2070481.2070509"},{"key":"18032_CR25","doi-asserted-by":"crossref","unstructured":"Xiao J, Luo X (2022) A survey of sentiment analysis based on multi-modal information. In: 2022 IEEE Asia\u2013Pacific conference on image processing, electronics and computers (IPEC), pp 712\u2013715. IEEE","DOI":"10.1109\/IPEC54454.2022.9777333"},{"key":"18032_CR26","doi-asserted-by":"crossref","unstructured":"Zhou S, Jia J, Wang Q, Dong Y, Yin Y, Lei K (2018) Inferring emotion from conversational voice data: a semi\u2013supervised multi-path generative neural network approach. In: Proceedings of the AAAI conference on Artificial Intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.11280"},{"key":"18032_CR27","doi-asserted-by":"publisher","first-page":"35276","DOI":"10.1109\/ACCESS.2020.2975036","volume":"8","author":"K Zhang","year":"2020","unstructured":"Zhang K, Zhu Y, Zhang W, Zhang W, Zhu Y (2020) Transfer correlation between textual content to images for sentiment analysis. IEEE Access 8:35276\u201335289","journal-title":"IEEE Access"},{"issue":"1","key":"18032_CR28","doi-asserted-by":"publisher","first-page":"53","DOI":"10.5772\/54002","volume":"10","author":"S Dobri\u0161ek","year":"2013","unstructured":"Dobri\u0161ek S, Gaj\u0161ek R, Miheli\u010d F, Pave\u0161i\u0107 N, \u0160truc V (2013) Towards efficient multi-modal emotion recognition. Int J Adv Robot Syst 10(1):53","journal-title":"Int J Adv Robot Syst"},{"key":"18032_CR29","doi-asserted-by":"crossref","unstructured":"Poria S, Cambria E, Gelbukh A (2015) Deep convolutional neural network textual features and multiple kernel learning for utterance\u2013level multimodal sentiment analysis. In: Proceedings of the 2015 conference on empirical methods in natural language processing, pp 2539\u20132544","DOI":"10.18653\/v1\/D15-1303"},{"issue":"4","key":"18032_CR30","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.1109\/TMM.2018.2867718","volume":"21","author":"R Ji","year":"2018","unstructured":"Ji R, Chen F, Cao L, Gao Y (2018) Cross-modality microblog sentiment prediction via bi-layer multimodal hypergraph learning. IEEE Transactions on Multimedia 21(4):1062\u20131075","journal-title":"IEEE Transactions on Multimedia"},{"key":"18032_CR31","doi-asserted-by":"crossref","unstructured":"Akhtar MS, Chauhan DS, Ghosal D, Poria S, Ekbal A, Bhattacharyya P (2019) Multi-task learning for multi-modal emotion recognition and sentiment analysis. arXiv:1905.05812","DOI":"10.18653\/v1\/N19-1034"},{"key":"18032_CR32","doi-asserted-by":"crossref","unstructured":"Tsai Y\u2013HH, Ma MQ, Yang M, Salakhutdinov R, Morency L\u2013P (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. NIH Public Access","DOI":"10.18653\/v1\/2020.emnlp-main.143"},{"key":"18032_CR33","unstructured":"Matthew E (2018) Peters, mark neumann, mohit iyyer, matt gardner, christopher clark, kenton lee, luke zettlemoyer. deep contextualized word representations. In: Proc. of NAACL, vol 5"},{"key":"18032_CR34","unstructured":"Radford A, Narasimhan K, Salimans T, Sutskever I et al (2018) Improving language understanding by generative pre\u2013training"},{"key":"18032_CR35","unstructured":"Devlin J, Chang M\u2013W, Lee K, Toutanova K (2018) Bert: pre\u2013training of deep bidirectional transformers for language understanding. arXiv:1810.04805"},{"issue":"23","key":"18032_CR36","doi-asserted-by":"publisher","first-page":"33067","DOI":"10.1007\/s11042-022-13155-w","volume":"81","author":"B Gupta","year":"2022","unstructured":"Gupta B, Prakasam P, Velmurugan T (2022) Integrated bert embeddings, bilstmbigru and 1-d cnn model for binary sentiment classification analysis of movie reviews. Multimedia Tools Appl 81(23):33067\u201333086","journal-title":"Multimedia Tools Appl"},{"key":"18032_CR37","doi-asserted-by":"crossref","unstructured":"Gao S, Chen X, Ren Z, Zhao D, Yan R (2020) From standard summarization to new tasks and beyond: Summarization with manifold information. arXiv:2005.04684","DOI":"10.24963\/ijcai.2020\/676"},{"key":"18032_CR38","doi-asserted-by":"crossref","unstructured":"Hazarika D, Zimmermann R, Poria S (2020) Misa: Modality\u2013invariant and\u2013specific representations for multimodal sentiment analysis. In: Proceedings of the 28th ACM international conference on multimedia, pp 1122\u20131131","DOI":"10.1145\/3394171.3413678"},{"issue":"8","key":"18032_CR39","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"18032_CR40","doi-asserted-by":"crossref","unstructured":"Cho K, Van Merri\u00ebnboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using rnn encoderdecoder for statistical machine translation. arXiv:1406.1078","DOI":"10.3115\/v1\/D14-1179"},{"key":"18032_CR41","doi-asserted-by":"crossref","unstructured":"Lei T, Zhang Y,Wang SI, Dai H, Artzi Y (2017) Simple recurrent units for highly parallelizable recurrence. arXiv:1709.02755","DOI":"10.18653\/v1\/D18-1477"},{"key":"18032_CR42","unstructured":"Zadeh A, Zellers R, Pincus E, Morency L\u2013P (2016) Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. arXiv:1606.06259"},{"key":"18032_CR43","doi-asserted-by":"crossref","unstructured":"Zadeh AB, Liang PP, Poria S, Cambria E, Morency L\u2013P (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 (vol 1: Long Papers), pp 2236\u20132246","DOI":"10.18653\/v1\/P18-1208"},{"key":"18032_CR44","unstructured":"Tsai Y\u2013HH, Liang PP, Zadeh A, Morency L\u2013P, Salakhutdinov R (2018) Learning factorized multimodal representations. arXiv:1806.06176"},{"key":"18032_CR45","doi-asserted-by":"crossref","unstructured":"Tsai Y\u2013HH, Bai S, Liang PP, Kolter JZ, Morency L\u2013P, 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":"18032_CR46","doi-asserted-by":"crossref","unstructured":"Rahman W, Hasan MK, Lee S, Zadeh A, Mao C, Morency L\u2013P, Hoque E (2020) Integrating multimodal information in large pretrained transformers. In: Proceedings of the conference. Association for Computational Linguistics. Meeting, vol 2020, pp 2359. NIH Public Access","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"18032_CR47","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":"18032_CR48","doi-asserted-by":"publisher","first-page":"109259","DOI":"10.1016\/j.patcog.2022.109259","volume":"136","author":"D Wang","year":"2023","unstructured":"Wang D, Guo X, Tian Y, Liu J, He L, Luo X (2023) Tetfn: a text enhanced transformer fusion network for multimodal sentiment analysis. Pattern Recognit 136:109259","journal-title":"Pattern Recognit"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-18032-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-18032-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-18032-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T16:20:17Z","timestamp":1720196417000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-18032-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,11]]},"references-count":48,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["18032"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-18032-8","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,11]]},"assertion":[{"value":"27 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 September 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 December 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"The authors declare that they have no confict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}