{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T06:25:04Z","timestamp":1793687104099,"version":"4.5.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Symbiosis International"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-09000-3","type":"journal-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T22:58:23Z","timestamp":1752533903000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Hierarchical cross-modal attention and dual audio pathways for enhanced multimodal sentiment analysis"],"prefix":"10.1038","volume":"15","author":[{"given":"D.","family":"Vamsidhar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Parth","family":"Desai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aniket K.","family":"Shahade","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shruti","family":"Patil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Priyanka V.","family":"Deshmukh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"9000_CR1","unstructured":"Dey, L., Chakraborty, S., Biswas, A., Bose, B. & Tiwari, S. Sentiment analysis of review datasets using Naive Bayes and k-nn classifier. arXiv preprint arXiv:1610.09982 (2016)."},{"issue":"5","key":"9000_CR2","first-page":"25","volume":"177","author":"M Ahmad","year":"2017","unstructured":"Ahmad, M., Aftab, S. & Ali, I. Sentiment analysis of tweets using svm. Int. J. Comput. Appl. 177(5), 25\u201329 (2017).","journal-title":"Int. J. Comput. Appl."},{"key":"9000_CR3","unstructured":"Ain, Q. T. et al. Sentiment analysis using deep learning techniques: A review. Int. J. Adv. Comput. Sci. Appl. 8(6) (2017)."},{"key":"9000_CR4","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1016\/j.procs.2017.06.037","volume":"111","author":"S Liao","year":"2017","unstructured":"Liao, S., Wang, J., Yu, R., Sato, K. & Cheng, Z. CNN for situations understanding based on sentiment analysis of twitter data. Procedia Comput. Sci. 111, 376\u2013381 (2017).","journal-title":"Procedia Comput. Sci."},{"key":"9000_CR5","unstructured":"Hoang, M., Bihorac, O. A. & Rouces, J. Aspect-based sentiment analysis using bert. In Proceedings of the 22nd Nordic Conference on Computational Linguistics 187\u2013196 (2019)."},{"issue":"13s","key":"9000_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3586075","volume":"55","author":"R Das","year":"2023","unstructured":"Das, R. & Singh, T. D. Multimodal sentiment analysis: A survey of methods, trends, and challenges. ACM Comput. Surv. 55(13s), 1\u201338 (2023).","journal-title":"ACM Comput. Surv."},{"key":"9000_CR7","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. Multimodal sentiment analysis: A systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions. Inf. Fusion 91, 424\u2013444 (2023).","journal-title":"Inf. Fusion"},{"key":"9000_CR8","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.imavis.2017.08.003","volume":"65","author":"M Soleymani","year":"2017","unstructured":"Soleymani, M. et al. A survey of multimodal sentiment analysis. Image Vis. Comput. 65, 3\u201314 (2017).","journal-title":"Image Vis. Comput."},{"key":"9000_CR9","unstructured":"Yadav, S. K., Bhushan, M., Gupta, S. & Multimodal sentiment analysis: Sentiment analysis using audiovisual format. In 2nd International Conference on Computing for Sustainable Global Development (indiacom), 2015 1415\u20131419 (IEEE, 2015)."},{"issue":"2","key":"9000_CR10","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/s13735-019-00185-8","volume":"9","author":"MG Huddar","year":"2020","unstructured":"Huddar, M. G., Sannakki, S. S. & Rajpurohit, V. S. Multi-level context extraction and attention-based contextual inter-modal fusion for multimodal sentiment analysis and emotion classification. Int. J. Multimed. Inf. Retr. 9(2), 103\u2013112 (2020).","journal-title":"Int. J. Multimed. Inf. Retr."},{"key":"9000_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2022.100157","volume":"14","author":"ST Kokab","year":"2022","unstructured":"Kokab, S. T., Asghar, S. & Naz, S. Transformer-based deep learning models for the sentiment analysis of social media data. Array 14, 100157 (2022).","journal-title":"Array"},{"key":"9000_CR12","doi-asserted-by":"crossref","unstructured":"Xu, H. Unimodal sentiment analysis. In Multi-Modal Sentiment Analysis 135\u2013177 (Springer, 2023).","DOI":"10.1007\/978-981-99-5776-7_4"},{"key":"9000_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126974","volume":"276","author":"X Zhao","year":"2025","unstructured":"Zhao, X., Poria, S., Li, X., Chen, Y. & Tang, B. Toward robust multimodal sentiment analysis using multimodal foundational models. Expert Syst. Appl. 276, 126974 (2025).","journal-title":"Expert Syst. Appl."},{"key":"9000_CR14","unstructured":"Zadeh, A. et al. CMU multimodal opinion sentiment and emotion intensity dataset. Accessed May 2025. http:\/\/multicomp.cs.cmu.edu\/resources\/cmu-mosi-dataset\/."},{"key":"9000_CR15","unstructured":"Zadeh, A. B., Liang, P. P., Poria, S., Cambria, E. & Morency, L. P. 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, 2236\u20132246 (2018)."},{"key":"9000_CR16","doi-asserted-by":"publisher","first-page":"4014","DOI":"10.1109\/TMM.2020.3035277","volume":"23","author":"X Yang","year":"2020","unstructured":"Yang, X., Feng, S., Wang, D. & Zhang, Y. Image-text multimodal emotion classification via multi-view attentional network. IEEE Trans. Multimed. 23, 4014\u20134026 (2020).","journal-title":"IEEE Trans. Multimed."},{"issue":"1","key":"9000_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3517139","volume":"19","author":"A Yadav","year":"2023","unstructured":"Yadav, A. & Vishwakarma, D. K. A deep multi-level attentive network for multimodal sentiment analysis. ACM Trans. Multimed. Comput. Commun. Appl. 19(1), 1\u201319 (2023).","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"issue":"2","key":"9000_CR18","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/s10772-023-10035-y","volume":"26","author":"M Tellai","year":"2023","unstructured":"Tellai, M., Gao, L. & Mao, Q. An efficient speech emotion recognition based on a dual-stream CNN-transformer fusion network. Int. J. Speech Technol. 26(2), 541\u2013557 (2023).","journal-title":"Int. J. Speech Technol."},{"issue":"4","key":"9000_CR19","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1007\/s10772-023-10080-7","volume":"26","author":"M Tellai","year":"2023","unstructured":"Tellai, M. & Mao, Q. CCTG-NET: Contextualized convolutional transformer-GRU network for speech emotion recognition. Int. J. Speech Technol. 26(4), 1099\u20131116 (2023).","journal-title":"Int. J. Speech Technol."},{"key":"9000_CR20","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C. et al. IEMOCAP: Interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42, 335\u2013359 (2008).","journal-title":"Lang. Resour. Eval."},{"issue":"21","key":"9000_CR21","doi-asserted-by":"publisher","first-page":"59699","DOI":"10.1007\/s11042-023-17803-7","volume":"83","author":"M Tellai","year":"2024","unstructured":"Tellai, M., Gao, L., Mao, Q. & Abdelaziz, M. A novel conversational hierarchical attention network for speech emotion recognition in dyadic conversation. Multimed. Tools Appl. 83(21), 59699\u201359723 (2024).","journal-title":"Multimed. Tools Appl."},{"issue":"11","key":"9000_CR22","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1080\/15563650.2021.1893742","volume":"59","author":"M Chenworth","year":"2021","unstructured":"Chenworth, M. et al. Methadone and suboxone\u00ae mentions on twitter: Thematic and sentiment analysis. Clin. Toxicol. 59(11), 982\u2013991 (2021).","journal-title":"Clin. Toxicol."},{"key":"9000_CR23","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1016\/j.inffus.2023.02.028","volume":"95","author":"L Zhu","year":"2023","unstructured":"Zhu, L., Zhu, Z., Zhang, C., Xu, Y. & Kong, X. Multimodal sentiment analysis based on fusion methods: A survey. Inf. Fusion 95, 306\u2013325 (2023).","journal-title":"Inf. Fusion"},{"key":"9000_CR24","doi-asserted-by":"crossref","unstructured":"Poria, S., Chaturvedi, I., Cambria, E. & Hussain A. Convolutional MKL based multimodal emotion recognition and sentiment analysis. In IEEE 16th International Conference on Data Mining (ICDM), 2016 439\u2013448 (IEEE, 2016).","DOI":"10.1109\/ICDM.2016.0055"},{"issue":"5","key":"9000_CR25","doi-asserted-by":"publisher","first-page":"4260","DOI":"10.1007\/s10489-024-05355-8","volume":"54","author":"S Yang","year":"2024","unstructured":"Yang, S., Cui, L., Wang, L. & Wang, T. Cross-modal contrastive learning for multimodal sentiment recognition. Appl. Intell. 54(5), 4260\u20134276 (2024).","journal-title":"Appl. Intell."},{"key":"9000_CR26","doi-asserted-by":"crossref","unstructured":"Wagh, R. & Punde, P. Survey on sentiment analysis using twitter dataset. In Second International Conference on Electronics, Communication and Aerospace Technology (ICECA), 2018 208\u2013211 (IEEE, 2018).","DOI":"10.1109\/ICECA.2018.8474783"},{"key":"9000_CR27","doi-asserted-by":"crossref","unstructured":"Shahade, A. K., Walse, K. H. & Thakare, V. M. Deep learning approach-based hybrid fine-tuned Smith algorithm with Adam optimiser for multilingual opinion mining. International Journal of Computer Applications in Technology, Vol. 73, 50\u201365. Accessed June 2025. https:\/\/www.inderscience.com\/info\/inarticle.php?artid=133253.","DOI":"10.1504\/IJCAT.2023.134080"},{"key":"9000_CR28","doi-asserted-by":"crossref","unstructured":"Poria, S., Hazarika, D., Majumder, N., Naik, G., Cambria, E. & Mihalcea, R. Meld: A multimodal multi-party dataset for emotion recognition in conversations. arXiv preprint arXiv:1810.02508 (2018).","DOI":"10.18653\/v1\/P19-1050"},{"key":"9000_CR29","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wan, Z. & Wan, X. Transmodality: An end2end fusion method with transformer for multimodal sentiment analysis. In Proceedings of the Web Conference 2020 2514\u20132520 (2020).","DOI":"10.1145\/3366423.3380000"},{"key":"9000_CR30","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-7474-6","volume-title":"Visual and Text Sentiment Analysis Through Hierarchical Deep Learning networks","author":"A Chaudhuri","year":"2019","unstructured":"Chaudhuri, A. Visual and Text Sentiment Analysis Through Hierarchical Deep Learning networks (Springer, 2019)."},{"key":"9000_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2022.102147","volume":"114","author":"F Lin","year":"2023","unstructured":"Lin, F., Liu, S., Zhang, C., Fan, J. & Wu, Z. StyleBERT: Text-audio sentiment analysis with bi-directional style enhancement. Inf. Syst. 114, 102147 (2023).","journal-title":"Inf. Syst."},{"key":"9000_CR32","doi-asserted-by":"crossref","unstructured":"Hasan, M. K., Rahman, W., Zadeh, A., Zhong, J., Tanveer, M. I., Morency, L. P. et al. UR-FUNNY: A multimodal language dataset for understanding humor. arXiv preprint arXiv:1904.06618 (2019).","DOI":"10.18653\/v1\/D19-1211"},{"key":"9000_CR33","doi-asserted-by":"crossref","unstructured":"Kakuba, S. & Han, D. S. Addressing Data Scarcity in Speech Emotion Recognition: A Comprehensive Review (ICT Express, 2024).","DOI":"10.1016\/j.icte.2024.11.003"},{"key":"9000_CR34","doi-asserted-by":"publisher","first-page":"113769","DOI":"10.1109\/ACCESS.2023.3325037","volume":"11","author":"S Kakuba","year":"2023","unstructured":"Kakuba, S., Poulose, A. & Han, D. S. Deep learning approaches for bimodal speech emotion recognition: Advancements, challenges, and a multi-learning model. IEEE Access 11, 113769\u2013113789 (2023).","journal-title":"IEEE Access"},{"issue":"1","key":"9000_CR35","doi-asserted-by":"publisher","first-page":"169","DOI":"10.18280\/isi.300114","volume":"30","author":"AK Shahade","year":"2025","unstructured":"Shahade, A. K. & Deshmukh, P. V. A unified approach to text summarization: Classical, machine learning, and deep learning methods. Ing\u00e9nierie des Syst\u00e8mes d\u2019Information 30(1), 169\u2013179. https:\/\/doi.org\/10.18280\/isi.300114 (2025).","journal-title":"Ing\u00e9nierie des Syst\u00e8mes d\u2019Information"},{"key":"9000_CR36","doi-asserted-by":"crossref","unstructured":"Rahman, W., Hasan, M. K., Lee, S., Zadeh, A., Mao, C., Morency, L. P., et al. Integrating multimodal information in large pretrained transformers. In Proceedings of the Conference. Association for Computational Linguistics. Meeting Vol. 2020, 2359 (2020).","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"9000_CR37","doi-asserted-by":"crossref","unstructured":"Sun, H., Wang, H., Liu, J., Chen, Y. W. & Lin, L. CubeMLP: An MLP-based model for multimodal sentiment analysis and depression estimation. In Proceedings of the 30th ACM International Conference on Multimedia 3722\u20133729 (2022).","DOI":"10.1145\/3503161.3548025"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-09000-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-09000-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-09000-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T09:43:25Z","timestamp":1757238205000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-09000-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,15]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["9000"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-09000-3","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,15]]},"assertion":[{"value":"11 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2025","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 declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"25440"}}