{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T00:44:09Z","timestamp":1777941849215,"version":"3.51.4"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,11,13]],"date-time":"2021-11-13T00:00:00Z","timestamp":1636761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,11,13]],"date-time":"2021-11-13T00:00:00Z","timestamp":1636761600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12171065"],"award-info":[{"award-number":["12171065"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11671001"],"award-info":[{"award-number":["11671001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Doctor Training Program of Chongqing University of Posts and Telecommunications","award":["BYJS201915"],"award-info":[{"award-number":["BYJS201915"]}]},{"name":"Doctor Training Program of Chongqing University of Posts and Telecommunications","award":["BYJS201907"],"award-info":[{"award-number":["BYJS201907"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2022,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Only the label corresponding to the maximum value of the fully connected layer is used as the output category when a neural network performs classification tasks. When the maximum value of the fully connected layer is close to the sub-maximum value, the classification obtained by considering only the maximum value and ignoring the sub-maximum value is not completely accurate. To reduce the noise and improve classification accuracy, combining the principles of fuzzy reasoning, this paper integrates all the output results of the fully connected layer with the emotional tendency of the text based on the dictionary to establish a multi-modal fuzzy recognition emotion enhancement model. The provided model considers the enhancement effect of negative words, degree adverbs, exclamation marks, and question marks based on the smallest subtree on the emotion of emotional words, and defines the global emotional membership function of emojis based on the corpus. Through comparing the results of CNN, LSTM, BiLSTM and GRU on Weibo and Douyin, it is shown that the provided model can effectively improve the text emotion recognition when the neural network output result is not clear, especially for long texts.<\/jats:p>","DOI":"10.1007\/s40747-021-00579-4","type":"journal-article","created":{"date-parts":[[2021,11,13]],"date-time":"2021-11-13T14:02:23Z","timestamp":1636812143000},"page":"1071-1084","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A multi-modal and multi-scale emotion-enhanced inference model based on fuzzy recognition"],"prefix":"10.1007","volume":"8","author":[{"given":"Yan","family":"Yu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4088-5371","authenticated-orcid":false,"given":"Dong","family":"Qiu","sequence":"additional","affiliation":[]},{"given":"Ruiteng","family":"Yan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,11,13]]},"reference":[{"key":"579_CR1","first-page":"1","volume":"99","author":"X Wang","year":"2020","unstructured":"Wang X, Kou L, Sugumaran V et al (2020) Emotion correlation mining through deep learning models on natural language text. IEEE Trans Cybern 99:1\u201314","journal-title":"IEEE Trans Cybern"},{"key":"579_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TAFFC.2020.3034050","volume":"99","author":"MC Pavan","year":"2020","unstructured":"Pavan MC, Dos Santos VG, Lan AGJ et al (2020) Morality classification in natural language text. IEEE Trans Affect Comput 99:1","journal-title":"IEEE Trans Affect Comput"},{"key":"579_CR3","doi-asserted-by":"crossref","unstructured":"Ayari N, Abdelkawy H, Chibani A et al (2020) Hybrid model-based emotion contextual recognition for cognitive assistance services. IEEE Trans Cybern 1\u201310","DOI":"10.1109\/TCYB.2020.3013112"},{"key":"579_CR4","doi-asserted-by":"publisher","first-page":"784","DOI":"10.1109\/TMM.2020.2990085","volume":"23","author":"Y Gao","year":"2021","unstructured":"Gao Y, Gong M, Xie Y et al (2021) An attention-based unsupervised adversarial model for movie review spam detection. IEEE Trans Multimed 23:784\u2013796","journal-title":"IEEE Trans Multimed"},{"key":"579_CR5","doi-asserted-by":"publisher","first-page":"1640","DOI":"10.1109\/TMM.2020.3001527","volume":"23","author":"X Yao","year":"2021","unstructured":"Yao X, She D, Zhang H et al (2021) Adaptive deep metric learning for affective image retrieval and classification. IEEE Trans Multimed 23:1640\u20131653","journal-title":"IEEE Trans Multimed"},{"key":"579_CR6","first-page":"1","volume":"99","author":"X Yang","year":"2020","unstructured":"Yang X, Feng S, Wang D et al (2020) Image-text multimodal emotion classification via multi-view attentional network. IEEE Trans Multimed 99:1","journal-title":"IEEE Trans Multimed"},{"key":"579_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TAFFC.2020.3015491","volume":"99","author":"M Firdaus","year":"2020","unstructured":"Firdaus M, Chauhan H, Ekbal A et al (2020) EmoSen: generating sentiment and emotion controlled responses in a multimodal dialogue system. IEEE Trans Affect Comput 99:1\u20131","journal-title":"IEEE Trans Affect Comput"},{"key":"579_CR8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TAFFC.2020.3034215","volume":"99","author":"J Deng","year":"2020","unstructured":"Deng J, Ren F (2020) Multi-label emotion detection via emotion-specified feature extraction and emotion correlation learning. IEEE Trans Affect Comput 99:1\u20131","journal-title":"IEEE Trans Affect Comput"},{"key":"579_CR9","first-page":"1","volume":"99","author":"O Wu","year":"2020","unstructured":"Wu O, Yang T, Li M et al (2020) Two-level LSTM for sentiment analysis with lexicon embedding and polar flipping. IEEE Trans Cybern 99:1\u201313","journal-title":"IEEE Trans Cybern"},{"key":"579_CR10","doi-asserted-by":"crossref","unstructured":"Yan R, Yu Y, Qiu D (2021) Emotion-enhanced classification based on fuzzy reasoning. Int J Mach Learn Cybern 1\u201312","DOI":"10.1007\/s13042-021-01356-y"},{"key":"579_CR11","doi-asserted-by":"publisher","unstructured":"Baaj I, Poli J P (2019) Natural language generation of explanations of fuzzy inference decisions. In: 2019 IEEE international conference on fuzzy systems (FUZZ-IEEE), pp 1\u20136. https:\/\/doi.org\/10.1109\/FUZZ-IEEE.2019.8858994","DOI":"10.1109\/FUZZ-IEEE.2019.8858994"},{"key":"579_CR12","doi-asserted-by":"crossref","unstructured":"Paul S, Ray K, Saha D (2020) Application of fuzzy answer set programming in hybrid deep neural-symbolic architecture. In: 2020 IEEE international conference for convergence in engineering, pp 105\u2013109. https:\/\/doi.org\/10.1109\/ICCE50343.2020.9290604","DOI":"10.1109\/ICCE50343.2020.9290604"},{"issue":"11","key":"579_CR13","doi-asserted-by":"publisher","first-page":"3023","DOI":"10.1109\/TFUZZ.2019.2947225","volume":"28","author":"X Lu","year":"2019","unstructured":"Lu X, Bai Y (2019) A new rule reduction method for fuzzy modeling. IEEE Trans Fuzzy Syst 28(11):3023\u20133031","journal-title":"IEEE Trans Fuzzy Syst"},{"issue":"9","key":"579_CR14","doi-asserted-by":"publisher","first-page":"1881","DOI":"10.1109\/TFUZZ.2019.2892354","volume":"27","author":"H Zhou","year":"2020","unstructured":"Zhou H, Ying H, Zhang C (2020) Effects of increasing the footprints of uncertainty on analytical structure of the classes of interval type-2 Mamdani and TS fuzzy controllers. IEEE Trans Fuzzy Syst 27(9):1881\u20131890","journal-title":"IEEE Trans Fuzzy Syst"},{"issue":"1","key":"579_CR15","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TFUZZ.2020.2986982","volume":"29","author":"M Ali","year":"2021","unstructured":"Ali M, Adnan M, Tariq M et al (2021) Load forecasting through estimated parametrized based fuzzy inference system in smart grids. IEEE Trans Fuzzy Syst 29(1):156\u2013165","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"579_CR16","first-page":"1","volume":"99","author":"P Gupta","year":"2020","unstructured":"Gupta P, Kumar S, Suman RR et al (2020) Sentiment analysis of lockdown in India during COVID-19: a case study on Twitter. IEEE Trans Comput Soc Syst 99:1\u201311","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"579_CR17","first-page":"1","volume":"99","author":"L Gui","year":"2020","unstructured":"Gui L, Jia L, Zhou J et al (2020) Multi-task learning with mutual learning for joint sentiment classification and topic detection. IEEE Trans Knowl Data Eng 99:1\u20131","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"579_CR18","doi-asserted-by":"crossref","unstructured":"Shobana J, Murali M (2021) An efficient sentiment analysis methodology based on long short-term memory networks. Complex Intell Syst 7:2485\u20132501","DOI":"10.1007\/s40747-021-00436-4"},{"key":"579_CR19","first-page":"1","volume":"99","author":"S Shekhar","year":"2021","unstructured":"Shekhar S, Garg H, Agrawal R et al (2021) Hatred and trolling detection transliteration framework using hierarchical LSTM in code-mixed social media text. Complex Intell Syst 99:1","journal-title":"Complex Intell Syst"},{"key":"579_CR20","first-page":"1","volume":"99","author":"S Mai","year":"2020","unstructured":"Mai S, Hu H, Xu J et al (2020) Multi-fusion residual memory network for multimodal human sentiment comprehension. IEEE Trans Affect Comput 99:1","journal-title":"IEEE Trans Affect Comput"},{"key":"579_CR21","first-page":"1","volume":"99","author":"M Huang","year":"2020","unstructured":"Huang M, Xie H, Rao Y et al (2020) Lexicon-based sentiment convolutional neural networks for online review analysis. IEEE Trans Affect Comput 99:1\u20131","journal-title":"IEEE Trans Affect Comput"},{"key":"579_CR22","first-page":"1","volume":"99","author":"T Zhou","year":"2020","unstructured":"Zhou T, Cao J, Zhu X et al (2020) Visual-textual sentiment analysis enhanced by hierarchical cross-modality interaction. IEEE Syst J 99:1\u201312","journal-title":"IEEE Syst J"},{"issue":"4","key":"579_CR23","doi-asserted-by":"publisher","first-page":"1919","DOI":"10.1007\/s40747-021-00295-z","volume":"7","author":"PT Krishnan","year":"2021","unstructured":"Krishnan PT, Joseph Raj AN, Rajangam V (2021) Emotion classification from speech signal based on empirical mode decomposition and non-linear features. Complex Intell Syst 7(4):1919\u20131934","journal-title":"Complex Intell Syst"},{"key":"579_CR24","first-page":"1","volume":"99","author":"K Ma","year":"2020","unstructured":"Ma K, Jiang B (2020) Voice of urban park visitors: exploring destination attributes influencing behavioural intentions through online review mining. Complex Intell Syst 99:1\u20131","journal-title":"Complex Intell Syst"},{"key":"579_CR25","first-page":"1","volume":"99","author":"N Xu","year":"2020","unstructured":"Xu N, Mao W, Wei P et al (2020) MDA: multimodal data augmentation framework for boosting performance on image-text sentiment\/emotion classification tasks. IEEE Intell Syst 99:1\u20131","journal-title":"IEEE Intell Syst"},{"key":"579_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TAFFC.2020.3038167","volume":"99","author":"S Poria","year":"2020","unstructured":"Poria S, Hazarika D, Majumder N et al (2020) Beneath the tip of the iceberg: current challenges and new directions in sentiment analysis research. IEEE Trans Affect Comput 99:1\u20131","journal-title":"IEEE Trans Affect Comput"},{"issue":"10","key":"579_CR27","doi-asserted-by":"publisher","first-page":"2026","DOI":"10.1109\/TKDE.2019.2913641","volume":"32","author":"L Wang","year":"2020","unstructured":"Wang L, Niu J, Yu S (2020) SentiDiff: combining textual information and sentiment diffusion patterns for Twitter sentiment analysis. IEEE Trans Knowl Data Eng 32(10):2026\u20132039","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"579_CR28","first-page":"1","volume":"99","author":"J Xu","year":"2020","unstructured":"Xu J, Li Z, Huang F et al (2020) Visual sentiment analysis with social relations-guided multiattention networks. IEEE Trans Cybern 99:1\u201313","journal-title":"IEEE Trans Cybern"},{"issue":"1","key":"579_CR29","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1145\/3297277","volume":"9","author":"JI Koh","year":"2019","unstructured":"Koh JI, Cherian J, Taele P et al (2019) Developing a hand gesture recognition system for mapping symbolic hand gestures to analogous emojis in computer-mediated communication. ACM Trans Interact Intell Syst 9(1):134\u2013168","journal-title":"ACM Trans Interact Intell Syst"},{"issue":"8","key":"579_CR30","doi-asserted-by":"publisher","first-page":"1748","DOI":"10.1108\/IMDS-01-2019-0001","volume":"119","author":"M Li","year":"2019","unstructured":"Li M, Chng E, Chong A et al (2019) An empirical analysis of emoji usage on Twitter. Ind Manag Data Syst 119(8):1748\u20131763","journal-title":"Ind Manag Data Syst"},{"issue":"3","key":"579_CR31","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1108\/IJWIS-09-2019-0042","volume":"16","author":"T Tomihira","year":"2020","unstructured":"Tomihira T, Otsuka A, Yamashita A et al (2020) Multilingual emoji prediction using BERT for sentiment analysis. Int J Web Inf Syst 16(3):265\u2013280","journal-title":"Int J Web Inf Syst"},{"issue":"2","key":"579_CR32","doi-asserted-by":"publisher","first-page":"11:1","DOI":"10.1145\/3377479","volume":"3","author":"A Robertson","year":"2020","unstructured":"Robertson A, Magdy W, Goldwater S (2020) Emoji skin tone modifiers: analyzing variation in usage on social media. ACM Trans Soc Comput 3(2):11:1-11:25","journal-title":"ACM Trans Soc Comput"},{"issue":"2","key":"579_CR33","doi-asserted-by":"publisher","first-page":"6:1","DOI":"10.1145\/3386120","volume":"3","author":"S Wijeratne","year":"2020","unstructured":"Wijeratne S, Saggion H, Kiciman E et al (2020) Emoji understanding and applications in social media: lay of the land and special issue introduction. ACM Trans Soc Comput 3(2):6:1-6:5","journal-title":"ACM Trans Soc Comput"},{"key":"579_CR34","doi-asserted-by":"crossref","unstructured":"Wiegand M, Ruppenhofer J (2021) Exploiting emojis for abusive language detection. In: Proceedings of the 16th conference of the European chapter of the association for computational linguistics, pp 369\u2013380. https:\/\/doi.org\/10.18653\/v1\/2021.eacl-main.28","DOI":"10.18653\/v1\/2021.eacl-main.28"},{"issue":"2","key":"579_CR35","doi-asserted-by":"publisher","first-page":"9:1","DOI":"10.1145\/3373146","volume":"3","author":"J Kim","year":"2020","unstructured":"Kim J, Gong T, Kim B et al (2020) No more one liners: bringing context into emoji recommendations. ACM Trans Soc Comput 3(2):9:1-9:25","journal-title":"ACM Trans Soc Comput"},{"issue":"1","key":"579_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3039685","volume":"24","author":"H Pohl","year":"2017","unstructured":"Pohl H, Domin C, Rohs M (2017) Beyond just text: semantic emoji similarity modeling to support expressive communication. ACM Trans Comput Hum Interact 24(1):1\u201342","journal-title":"ACM Trans Comput Hum Interact"},{"issue":"2","key":"579_CR37","doi-asserted-by":"publisher","first-page":"106727","DOI":"10.1016\/j.knosys.2020.106727","volume":"214","author":"D Peng","year":"2021","unstructured":"Peng D, Zhao H (2021) Seq2Emoji: a hybrid sequence generation model for short text emoji prediction. Knowl Based Syst 214(2):106727","journal-title":"Knowl Based Syst"},{"issue":"2","key":"579_CR38","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s12559-020-09715-7","volume":"13","author":"C Suman","year":"2021","unstructured":"Suman C, Saha S, Bhattacharyya P et al (2021) Emoji helps! A multi-modal Siamese architecture for Tweet user verification. Cogn Comput 13(2):261\u2013276","journal-title":"Cogn Comput"},{"issue":"4","key":"579_CR39","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1007\/s10339-020-00971-x","volume":"21","author":"P Wicke","year":"2020","unstructured":"Wicke P, Bolognesi M (2020) Emoji-based semantic representations for abstract and concrete concepts. Cogn Process 21(4):615\u2013635","journal-title":"Cogn Process"},{"issue":"5","key":"579_CR40","doi-asserted-by":"publisher","first-page":"64:1","DOI":"10.1145\/3389035","volume":"19","author":"Y Lou","year":"2020","unstructured":"Lou Y, Zhang Y, Li F et al (2020) Emoji-based sentiment analysis using attention networks. ACM Trans Asian Low Resour Lang Inf Process 19(5):64:1-64:13","journal-title":"ACM Trans Asian Low Resour Lang Inf Process"},{"key":"579_CR41","doi-asserted-by":"publisher","unstructured":"Boy S, Ruiter D, Klakow D (2021) Emoji-based transfer learning for sentiment tasks. In: Proceedings of the 16th conference of the European chapter of the association for computational linguistics, pp 103-110. https:\/\/doi.org\/10.18653\/v1\/2021.eacl-srw.15","DOI":"10.18653\/v1\/2021.eacl-srw.15"},{"issue":"2","key":"579_CR42","first-page":"18:1","volume":"30","author":"Z Chen","year":"2021","unstructured":"Chen Z, Cao Y, Yao H et al (2021) Emoji-powered sentiment and emotion detection from software developers\u2019 communication data. ACM Trans Softw Eng Methodol (TOSEM) 30(2):18:1-18:48","journal-title":"ACM Trans Softw Eng Methodol (TOSEM)"},{"issue":"aug.","key":"579_CR43","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.eswa.2018.02.043","volume":"103","author":"M Fernandez-Gavilanes","year":"2018","unstructured":"Fernandez-Gavilanes M, Juncal-Martinez J, Garcia-Mendez S et al (2018) Creating emoji lexica from unsupervised sentiment analysis of their descriptions. Expert Syst Appl 103(aug.):74\u201391","journal-title":"Expert Syst Appl"},{"issue":"2","key":"579_CR44","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1109\/TMM.2018.2862363","volume":"21","author":"S Cappallo","year":"2019","unstructured":"Cappallo S, Svetlichnaya S, Garrigues P et al (2019) New modality: emoji challenges in prediction, anticipation, and retrieval. IEEE Trans Multimed 21(2):402\u2013415","journal-title":"IEEE Trans Multimed"},{"key":"579_CR45","first-page":"1","volume":"99","author":"G Zhao","year":"2020","unstructured":"Zhao G, Liu Z, Chao Y et al (2020) CAPER: context-aware personalized emoji recommendation. IEEE Trans Knowl Data Eng 99:1\u20131","journal-title":"IEEE Trans Knowl Data Eng"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-021-00579-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-021-00579-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-021-00579-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T03:52:22Z","timestamp":1673754742000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-021-00579-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,13]]},"references-count":45,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["579"],"URL":"https:\/\/doi.org\/10.1007\/s40747-021-00579-4","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,13]]},"assertion":[{"value":"6 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 October 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflicts of interest regarding the publication of this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}