{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:57:01Z","timestamp":1775246221261,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319771151","type":"print"},{"value":"9783319771168","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-77116-8_13","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T23:56:00Z","timestamp":1539042960000},"page":"166-179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":42,"title":["Benchmarking Multimodal Sentiment Analysis"],"prefix":"10.1007","author":[{"given":"Erik","family":"Cambria","sequence":"first","affiliation":[]},{"given":"Devamanyu","family":"Hazarika","sequence":"additional","affiliation":[]},{"given":"Soujanya","family":"Poria","sequence":"additional","affiliation":[]},{"given":"Amir","family":"Hussain","sequence":"additional","affiliation":[]},{"given":"R. B. V.","family":"Subramanyam","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,10]]},"reference":[{"key":"13_CR1","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.inffus.2017.02.003","volume":"37","author":"S Poria","year":"2017","unstructured":"Poria, S., Cambria, E., Bajpai, R., Hussain, A.: A review of affective computing: from unimodal analysis to multimodal fusion. Inf. Fusion 37, 98\u2013125 (2017)","journal-title":"Inf. Fusion"},{"key":"13_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1007\/978-3-642-12397-9_12","volume-title":"Development of Multimodal Interfaces: Active Listening and Synchrony","author":"E Cambria","year":"2010","unstructured":"Cambria, E., Hussain, A., Havasi, C., Eckl, C.: Sentic computing: exploitation of common sense for the development of emotion-sensitive systems. In: Esposito, A., Campbell, N., Vogel, C., Hussain, A., Nijholt, A. (eds.) Development of Multimodal Interfaces: Active Listening and Synchrony. LNCS, vol. 5967, pp. 148\u2013156. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-12397-9_12"},{"key":"13_CR3","unstructured":"P\u00e9rez-Rosas, V., Mihalcea, R., Morency, L.P.: Utterance-level multimodal sentiment analysis. In: ACL, pp. 973\u2013982 (2013)"},{"key":"13_CR4","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/MIS.2013.34","volume":"28","author":"M Wollmer","year":"2013","unstructured":"Wollmer, M., Weninger, F., Knaup, T., Schuller, B., Sun, C., Sagae, K., Morency, L.P.: Youtube movie reviews: sentiment analysis in an audio-visual context. IEEE Intell. Syst. 28, 46\u201353 (2013)","journal-title":"IEEE Intell. Syst."},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Poria, S., Cambria, E., Gelbukh, A.: Deep convolutional neural network textual features and multiple kernel learning for utterance-level multimodal sentiment analysis. In: Proceedings of EMNLP, pp. 2539\u20132544","DOI":"10.18653\/v1\/D15-1303"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Zadeh, A.: Micro-opinion sentiment intensity analysis and summarization in online videos. In: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, pp. 587\u2013591. ACM (2015)","DOI":"10.1145\/2818346.2823317"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Poria, S., Chaturvedi, I., Cambria, E., Hussain, A.: Convolutional MKL based multimodal emotion recognition and sentiment analysis. In: ICDM, Barcelona, pp. 439\u2013448 (2016)","DOI":"10.1109\/ICDM.2016.0055"},{"key":"13_CR8","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1109\/MIS.2016.31","volume":"31","author":"E Cambria","year":"2016","unstructured":"Cambria, E.: Affective computing and sentiment analysis. IEEE Intell. Syst. 31, 102\u2013107 (2016)","journal-title":"IEEE Intell. Syst."},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Cambria, E., Poria, S., Hazarika, D., Kwok, K.: SenticNet 5: discovering conceptual primitives for sentiment analysis by means of context embeddings. In: AAAI, pp. 1795\u20131802 (2018)","DOI":"10.1609\/aaai.v32i1.11559"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Poria, S., Gelbukh, A., Agarwal, B., Cambria, E., Howard, N.: Advances in soft computing and its applications. In: Common Sense Knowledge Based Personality Recognition From Text, pp. 484\u2013496. Springer (2013)","DOI":"10.1007\/978-3-642-45111-9_42"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Pang, B., Lee, L., Vaithyanathan, S.: Thumbs up? Sentiment classification using machine learning techniques. In: Proceedings of ACL, pp. 79\u201386 (2002)","DOI":"10.3115\/1118693.1118704"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Socher, R., Perelygin, A., Wu, J.Y., Chuang, J., Manning, C.D., Ng, A.Y., Potts, C.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of EMNLP, vol. 1631, p. 1642 (2013)","DOI":"10.18653\/v1\/D13-1170"},{"key":"13_CR13","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/MCI.2016.2572540","volume":"11","author":"L Oneto","year":"2016","unstructured":"Oneto, L., Bisio, F., Cambria, E., Anguita, D.: Statistical learning theory and ELM for big social data analysis. IEEE Comput. Intell. Mag. 11, 45\u201355 (2016)","journal-title":"IEEE Comput. Intell. Mag."},{"key":"13_CR14","unstructured":"Ekman, P.: Universal facial expressions of emotion. Contemporary Readings\/Chicago, Culture and Personality (1974)"},{"key":"13_CR15","unstructured":"Datcu, D., Rothkrantz, L.: Semantic audio-visual data fusion for automatic emotion recognition. Euromedia (2008)"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"De Silva, L.C., Miyasato, T., Nakatsu, R.: Facial emotion recognition using multi-modal information. In: Proceedings of ICICS, vol. 1, pp. 397\u2013401. IEEE (1997)","DOI":"10.1109\/ICICS.1997.647126"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Chen, L.S., Huang, T.S., Miyasato, T., Nakatsu, R.: Multimodal human emotion\/expression recognition. In: Proceedings of the Third IEEE International Conference on Automatic Face and Gesture Recognition, pp. 366\u2013371. IEEE (1998)","DOI":"10.1109\/AFGR.1998.670976"},{"key":"13_CR18","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s12193-009-0025-5","volume":"3","author":"L Kessous","year":"2010","unstructured":"Kessous, L., Castellano, G., Caridakis, G.: Multimodal emotion recognition in speech-based interaction using facial expression, body gesture and acoustic analysis. J. Multimodal User Interfaces 3, 33\u201348 (2010)","journal-title":"J. Multimodal User Interfaces"},{"key":"13_CR19","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1109\/T-AFFC.2011.17","volume":"2","author":"B Schuller","year":"2011","unstructured":"Schuller, B.: Recognizing affect from linguistic information in 3D continuous space. IEEE Trans. Affect. Comput. 2, 192\u2013205 (2011)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"13_CR20","unstructured":"Rozgic, V., Ananthakrishnan, S., Saleem, S., Kumar, R., Prasad, R.: Ensemble of SVM trees for multimodal emotion recognition. In: IEEE APSIPA, pp. 1\u20134 (2012)"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Metallinou, A., Lee, S., Narayanan, S.: Audio-visual emotion recognition using Gaussian mixture models for face and voice. In: Tenth IEEE International Symposium on ISM 2008, pp. 250\u2013257. IEEE (2008)","DOI":"10.1109\/ISM.2008.40"},{"key":"13_CR22","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/s12193-009-0032-6","volume":"3","author":"F Eyben","year":"2010","unstructured":"Eyben, F., W\u00f6llmer, M., Graves, A., Schuller, B., Douglas-Cowie, E., Cowie, R.: On-line emotion recognition in a 3D activation-valence-time continuum using acoustic and linguistic cues. J. Multimodal User Interfaces 3, 7\u201319 (2010)","journal-title":"J. Multimodal User Interfaces"},{"key":"13_CR23","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/T-AFFC.2010.16","volume":"2","author":"CH Wu","year":"2011","unstructured":"Wu, C.H., Liang, W.B.: Emotion recognition of affective speech based on multiple classifiers using acoustic-prosodic information and semantic labels. IEEE Trans. Affect. Comput. 2, 10\u201321 (2011)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"13_CR24","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space (2013). arXiv preprint arXiv:1301.3781"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.: Opensmile: the Munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM International Conference on Multimedia, pp. 1459\u20131462. ACM (2010)","DOI":"10.1145\/1873951.1874246"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Baltru\u0161aitis, T., Robinson, P., Morency, L.P.: 3D constrained local model for rigid and non-rigid facial tracking. In: IEEE CVPR, pp. 2610\u20132617 (2012)","DOI":"10.1109\/CVPR.2012.6247980"},{"key":"13_CR27","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.: Multimodal sentiment intensity analysis in videos: facial gestures and verbal messages. IEEE Intell. Syst. 31, 82\u201388 (2016)","journal-title":"IEEE Intell. Syst."},{"key":"13_CR28","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C., Bulut, M., Lee, C.C., Kazemzadeh, A., Mower, E., Kim, S., Chang, J.N., Lee, S., Narayanan, S.S.: Iemocap: interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42, 335\u2013359 (2008)","journal-title":"Lang. Resour. Eval."},{"key":"13_CR29","unstructured":"Rozgi\u0107, V., Ananthakrishnan, S., Saleem, S., Kumar, R., Prasad, R.: Ensemble of SVM trees for multimodal emotion recognition. In: IEEE APSIPA, pp. 1\u20134 (2012)"}],"container-title":["Lecture Notes in Computer Science","Computational Linguistics and Intelligent Text Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-77116-8_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:03:04Z","timestamp":1775242984000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-77116-8_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319771151","9783319771168"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-77116-8_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"CICLing","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Linguistics and Intelligent Text Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Budapest","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 April 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 April 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicling2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cicling.org\/2017\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}