{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T10:17:06Z","timestamp":1779013026539,"version":"3.51.4"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T00:00:00Z","timestamp":1771372800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T00:00:00Z","timestamp":1774483200000},"content-version":"vor","delay-in-days":36,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Ment Health"],"DOI":"10.1007\/s44192-026-00388-6","type":"journal-article","created":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T07:26:18Z","timestamp":1771399578000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A unified multimodal learning framework for sentiment analysis and mental health indicators from YouTube videos"],"prefix":"10.1007","volume":"6","author":[{"given":"Priyanshu","family":"Satapathy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Onushka","family":"Chauhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deepika","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Preeti","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sumit Kumar","family":"Banshal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8347-8733","authenticated-orcid":false,"given":"Oana","family":"Geman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6588-989X","authenticated-orcid":false,"given":"Lucia","family":"Morosan-Danila","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jude D.","family":"Hemanth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,18]]},"reference":[{"key":"388_CR1","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.cosrev.2017.10.002","volume":"27","author":"MV M\u00e4ntyl\u00e4","year":"2018","unstructured":"M\u00e4ntyl\u00e4 MV, Graziotin D, Kuutila M. The evolution of sentiment analysis\u2014a review of research topics, venues, and top cited papers. Comput Sci Rev. 2018;27:16\u201332.","journal-title":"Comput Sci Rev"},{"issue":"3","key":"388_CR2","doi-asserted-by":"publisher","first-page":"3550","DOI":"10.1109\/TCSS.2023.3322002","volume":"11","author":"L Chaudhary","year":"2023","unstructured":"Chaudhary L, Girdhar N, Sharma D, Andreu-Perez J, Doucet A, Renz M. A review of deep learning models for Twitter sentiment analysis: challenges and opportunities. IEEE Trans Comput Social Syst. 2023;11(3):3550\u201379.","journal-title":"IEEE Trans Comput Social Syst"},{"key":"388_CR3","unstructured":"Liu B. Sentiment analysis and subjectivity. In: Handbook of natural language processing 2.2010. 2010. pp. 627\u2013666."},{"issue":"1","key":"388_CR4","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1146\/annurev-linguistics-011415-040518","volume":"2","author":"M Taboada","year":"2016","unstructured":"Taboada M. Sentiment analysis: an overview from linguistics. Ann Rev Linguist. 2016;2(1):325\u201347.","journal-title":"Annual Rev Linguistics"},{"issue":"1","key":"388_CR5","first-page":"178","volume":"2","author":"V Sahayak","year":"2015","unstructured":"Sahayak V, Shete V, Pathan A. Sentiment analysis on Twitter data. Int J Innov Res Adv Eng (IJIRAE). 2015;2(1):178\u201383.","journal-title":"Int J Innovative Res Adv Eng (IJIRAE)"},{"key":"388_CR6","doi-asserted-by":"crossref","unstructured":"Sarlan A, Nadam C, Basri S. Twitter sentiment analysis. In: Proceedings of the 6th International conference on Information TechnologyMultimedia. IEEE; 2014.","DOI":"10.1109\/ICIMU.2014.7066632"},{"key":"388_CR7","doi-asserted-by":"crossref","unstructured":"Albladi A, Islam M, Seals C. Sentiment analysis of Twitter data using NLP models: a comprehensive review. IEEE Access. 2025.","DOI":"10.1109\/ACCESS.2025.3541494"},{"issue":"1","key":"388_CR8","doi-asserted-by":"publisher","first-page":"24438","DOI":"10.1038\/s41598-025-09794-2","volume":"15","author":"N Jonnala","year":"2025","unstructured":"Jonnala N, Surekha, et al. Leveraging hybrid model for accurate sentiment analysis of Twitter data. Sci Rep. 2025;15(1):24438.","journal-title":"Sci Rep"},{"issue":"2","key":"388_CR9","doi-asserted-by":"publisher","first-page":"475","DOI":"10.5530\/jscires.13.2.38","volume":"13","author":"A Kafi","year":"2024","unstructured":"Kafi A, Abdullah SK, Banshal N, Sultana, Gupta V. Source recommendation system using context-based classification: empirical study on multi-level ensemble methods. J Scientometr Res. 2024;13(2):475\u201384.","journal-title":"J Scientometr Res"},{"key":"388_CR10","doi-asserted-by":"crossref","unstructured":"Poria S et al. Fusing audio, visual and textual clues for sentiment analysis from multimodal content. Neurocomputing. 2016;174: 50\u201359.","DOI":"10.1016\/j.neucom.2015.01.095"},{"key":"388_CR11","doi-asserted-by":"crossref","unstructured":"Abburi H et al. Multimodal sentiment analysis using deep neural networks. In: International conference on mining intelligence and knowledge exploration. Springer, Cham; 2016.","DOI":"10.1007\/978-3-319-58130-9_6"},{"key":"388_CR12","doi-asserted-by":"crossref","unstructured":"Portes Q et al. Multimodal neural network for sentiment analysis in embedded systems. In: VISIGRAPP (5: VISAPP). 2021.","DOI":"10.5220\/0010224703870398"},{"key":"388_CR13","doi-asserted-by":"crossref","unstructured":"Huang G-B, Zhu Q-Y, Siew C-K. Extreme learning machine: theory and applications. Neurocomputing. 2006;70(1\u20133):489\u2013501.","DOI":"10.1016\/j.neucom.2005.12.126"},{"issue":"1","key":"388_CR14","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1186\/s40537-025-01268-6","volume":"12","author":"M Subramanian","year":"2025","unstructured":"Subramanian M, Veerappampalayam Easwaramoorthy S, Subbarayan N, Moorthy U. Empowering sentiment analysis in social media: a comprehensive approach to enhance the classification of abusive Tamil comments using transformer models. J Big Data. 2025;12(1):208.","journal-title":"J Big Data"},{"key":"388_CR15","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1016\/j.neucom.2014.01.067","volume":"149","author":"E Principi","year":"2015","unstructured":"Principi E, et al. Acoustic template-matching for automatic emergency state detection: an ELM based algorithm. Neurocomputing. 2015;149:426\u201334.","journal-title":"Neurocomputing"},{"issue":"2","key":"388_CR16","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/s11042-009-0344-2","volume":"49","author":"M Mansoorizadeh","year":"2010","unstructured":"Mansoorizadeh M, Charkari NM. Multimodal information fusion application to human emotion recognition from face and speech. Multimedia Tools Appl. 2010;49(2):277\u201397.","journal-title":"Multimedia Tools Appl"},{"issue":"4","key":"388_CR17","doi-asserted-by":"publisher","first-page":"1334","DOI":"10.1016\/j.jnca.2006.09.007","volume":"30","author":"H Gunes","year":"2007","unstructured":"Gunes H. Bi-modal emotion recognition from expressive face and body gestures. J Netw Comput Appl. 2007;30(4):1334\u201345.","journal-title":"J Netw Comput Appl"},{"key":"388_CR18","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.neunet.2014.10.001","volume":"61","author":"G Huang","year":"2015","unstructured":"Huang G, et al. Trends in extreme learning machines: a review. Neural Netw. 2015;61:32\u201348.","journal-title":"Neural Netw"},{"key":"388_CR19","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.neucom.2011.12.050","volume":"102","author":"S Decherchi","year":"2013","unstructured":"Decherchi S, et al. Circular-ELM for the reduced-reference assessment of perceived image quality. Neurocomputing. 2013;102:78\u201389.","journal-title":"Neurocomputing"},{"key":"388_CR20","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1016\/j.neucom.2014.01.064","volume":"149","author":"E Cambria","year":"2015","unstructured":"Cambria E, et al. An ELM-based model for affective analogical reasoning. Neurocomputing. 2015;149:443\u201355.","journal-title":"Neurocomputing"},{"key":"388_CR21","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.neunet.2014.10.005","volume":"63","author":"S Poria","year":"2015","unstructured":"Poria S, et al. Towards an intelligent framework for multimodal affective data analysis. Neural Netw. 2015;63:104\u201316.","journal-title":"Neural Netw"},{"key":"388_CR22","doi-asserted-by":"crossref","unstructured":"Kindra M, Dixit V, Gupta V. A fuzzy-based approach for characterization and identification of sentiments. In: Computational intelligence for information retrieval. CRC; 2021. pp. 219\u201336.","DOI":"10.1201\/9781003134138-12"},{"issue":"11","key":"388_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3766889","volume":"24","author":"M Yagnik","year":"2025","unstructured":"Yagnik M, Hashmi M, Kumar D, Jain K, Grover E, Hemanth JD. A multi-output BERT framework for abusive comment detection and sentiment analysis on Low-Resource Language. ACM Trans Asian Low-Resource Lang Inform Process. 2025;24(11):1\u201325.","journal-title":"ACM Trans Asian Low-Resource Lang Inform Process"},{"key":"388_CR24","doi-asserted-by":"crossref","unstructured":"Cambria E et al. Sentic blending: scalable multimodal fusion for the continuous interpretation of semantics and sentics. In: 2013 IEEE symposium on computational intelligence for human-like intelligence (CIHLI). IEEE; 2013.","DOI":"10.1109\/CIHLI.2013.6613272"},{"key":"388_CR25","first-page":"1","volume":"30","author":"D Smith-Mutegi","year":"2025","unstructured":"Smith-Mutegi D, Mamo Y, Kim J, Crompton H, McConnell M. Perceptions of STEM education and artificial intelligence: a Twitter sentiment analysis. Educ Inform Technol. 2025;30:1\u201318.","journal-title":"Educ Inform Technol"},{"key":"388_CR26","doi-asserted-by":"crossref","unstructured":"Tsai Y-HH, Bai S, Yamada M, Morency L-P, Salakhutdinov R. Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the 57th annual meeting of the association for computational linguistics; 2019. pp. 6558\u20136569.","DOI":"10.18653\/v1\/P19-1656"},{"key":"388_CR27","first-page":"154478","volume":"8","author":"J Yang","year":"2020","unstructured":"Yang J, Sun Y, Chen J, Li Y. Multimodal sentiment analysis using BERT-based cross-modal fusion. IEEE Access. 2020;8:154478\u201389.","journal-title":"IEEE Access"},{"key":"388_CR28","unstructured":"Yu W, Xu H, Wang Z, Shen HT. Vision-language transformer for multimodal sentiment analysis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops; 2021. pp. 251\u2013260."},{"issue":"3","key":"388_CR29","first-page":"1214","volume":"13","author":"S Mai","year":"2022","unstructured":"Mai S, Hu H, Xing S, Zong Y, Zhang B. Multimodal sentiment analysis with Temporal self-attention transformer. IEEE Trans Affect Comput. 2022;13(3):1214\u201325.","journal-title":"IEEE Trans Affect Comput"},{"key":"388_CR30","first-page":"1","volume":"89","author":"Y Wang","year":"2023","unstructured":"Wang Y, Guo D, Li J, Li B. Unified transformer framework for multimodal sentiment analysis. Inform Fus. 2023;89:1\u201312.","journal-title":"Inform Fusion"}],"container-title":["Discover Mental Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44192-026-00388-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44192-026-00388-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44192-026-00388-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T09:55:34Z","timestamp":1774518934000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44192-026-00388-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,18]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["388"],"URL":"https:\/\/doi.org\/10.1007\/s44192-026-00388-6","relation":{},"ISSN":["2731-4383"],"issn-type":[{"value":"2731-4383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,18]]},"assertion":[{"value":"3 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 2026","order":3,"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 and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they do not have any conflict of interest. The research was carried out bearing in mind the ethical and privacy-related issues. The videos accessed to obtain all data in the experiments were all publicly available and accessed using official APIs without circumventing restrictions or privacy settings. No user- authenticated, restricted or private content was gathered or examined. In a further attempt to reduce the privacy risks, a filtering system was implemented which blocked videos with sensitive personal data, blatant personal disclosures or content that might cause privacy issues. The analysis was conducted at the aggregated level of segment and no personally identifiable data were saved, deduced or made with reference to individual identities. Also, the suggested framework is not expected to give clinical, diagnostic, or individual-level measures; instead, it targets high-level sentiment and affective pattern analysis. These will guarantee the use of the data in a responsible manner and will bring the study to the standards of the ethical research when analysing publicly available user-generated content.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical standards"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Clinical trial number"}},{"value":"All authors have no affiliation with any organization with a direct or indirect financial interest in the subject matter discussed in the manuscript. All authors declare that they have no conflict of interest.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"46"}}