{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T04:27:12Z","timestamp":1790742432069,"version":"4.1.0"},"reference-count":39,"publisher":"Fuji Technology Press Ltd.","issue":"2","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62466029"],"award-info":[{"award-number":["62466029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Yunnan Natural Science Funds","award":["202201AT070157"],"award-info":[{"award-number":["202201AT070157"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JACIII","J. Adv. Comput. Intell. Intell. Inform."],"published-print":{"date-parts":[[2026,3,20]]},"abstract":"<jats:p>Multimodal sentiment analysis (MSA) is a crucial technique for understanding sentiment expression in social media, product reviews, and other multimedia content, and has been extensively studied in recent years. However, most of the existing MSA methods depend on large datasets. Collecting such data is costly and time-consuming, limiting the practical applicability of these models. To address this challenge, this paper proposes a few-shot multimodal sentiment analysis method based on dynamic adjustment and contrastive learning (DACL-FMSA). First, the method uses the BLIP model to generate semantic descriptions of images. These descriptions are then aligned with text inputs to bridge the semantic gap and enable more effective multimodal fusion. Second, based on the contrastive learning framework, the model\u2019s ability to capture emotional features is enhanced by generating diverse views of image and text data, thus improving performance in few-shot tasks. Finally, to further optimize the learning process, this study designs a dynamic learning rate adjustment method based on a long short-term memory network, which dynamically adjusts the learning rate according to gradient changes to accelerate model convergence and achieve better training results. The experimental results show that DACL-FMSA achieves significant performance improvements. It performed well across multiple benchmark datasets. For Twitter-15, Twitter-17, and MASAD, the accuracies were 61.88%, 54.00%, and 81.78%, respectively. The accuracies of MVSA-S and TumEmo were 67.89% and 54.42%, respectively. These results consistently demonstrate the effectiveness of the DACL-FMSA.<\/jats:p>","DOI":"10.20965\/jaciii.2026.p0472","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T15:02:06Z","timestamp":1773932526000},"page":"472-485","source":"Crossref","is-referenced-by-count":2,"title":["Few-Shot Multimodal Sentiment Analysis Based on Dynamic Adjustment and Contrastive Learning"],"prefix":"10.20965","volume":"30","author":[{"given":"Hongbin","family":"Wang","sequence":"first","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, No.727 Jingming South Road, Chenggong District, Kunming, Yunnan 650500, China"},{"name":"Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology, No.727 Jingming South Road, Chenggong District, Kunming, Yunnan 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuangqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, No.727 Jingming South Road, Chenggong District, Kunming, Yunnan 650500, China"},{"name":"Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology, No.727 Jingming South Road, Chenggong District, Kunming, Yunnan 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Xie","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, No.727 Jingming South Road, Chenggong District, Kunming, Yunnan 650500, China"},{"name":"Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology, No.727 Jingming South Road, Chenggong District, Kunming, Yunnan 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"8550","published-online":{"date-parts":[[2026,3,20]]},"reference":[{"key":"key-10.20965\/jaciii.2026.p0472-1","doi-asserted-by":"crossref","unstructured":"S. Lai, X. Hu, H. Xu, Z. Ren, and Z. Liu, \u201cMultimodal sentiment analysis: A survey,\u201d Displays, Vol.80, Article No.102563, 2023. https:\/\/doi.org\/10.1016\/j.displa.2023.102563","DOI":"10.1016\/j.displa.2023.102563"},{"key":"key-10.20965\/jaciii.2026.p0472-2","doi-asserted-by":"crossref","unstructured":"H. Yang et al., \u201cLarge language models meet text-centric multimodal sentiment analysis: A survey,\u201d arXiv:2406.08068, 2024. https:\/\/doi.org\/10.48550\/arXiv.2406.08068","DOI":"10.1007\/s11432-024-4593-8"},{"key":"key-10.20965\/jaciii.2026.p0472-3","doi-asserted-by":"crossref","unstructured":"X. Yang et al., \u201cFew-shot joint multimodal aspect-sentiment analysis based on generative multimodal prompt,\u201d arXiv:2305.10169, 2023. https:\/\/doi.org\/10.48550\/arXiv.2305.10169","DOI":"10.18653\/v1\/2023.findings-acl.735"},{"key":"key-10.20965\/jaciii.2026.p0472-4","doi-asserted-by":"crossref","unstructured":"P. Liu et al., \u201cPre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing,\u201d ACM Computing Surveys, Vol.55, No.9, Article No.195, 2023. https:\/\/doi.org\/10.1145\/3560815","DOI":"10.1145\/3560815"},{"key":"key-10.20965\/jaciii.2026.p0472-5","unstructured":"J. Li, D. Li, C. Xiong, and S. Hoi, \u201cBLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation,\u201d Proc. of the 39th Int. Conf. on Machine Learning, pp. 12888-12900, 2022."},{"key":"key-10.20965\/jaciii.2026.p0472-6","doi-asserted-by":"crossref","unstructured":"Y. Jian, C. Gao, and S. Vosoughi, \u201cContrastive learning for prompt-based few-shot language learners,\u201d arXiv:2205.01308, 2022. https:\/\/doi.org\/10.48550\/arXiv.2205.01308","DOI":"10.18653\/v1\/2022.naacl-main.408"},{"key":"key-10.20965\/jaciii.2026.p0472-7","doi-asserted-by":"crossref","unstructured":"X. Yang, S. Feng, D. Wang, Y. Zhang, and S. Poria, \u201cFew-shot multimodal sentiment analysis based on multimodal probabilistic fusion prompts,\u201d Proc. of the 31st ACM Int. Conf. on Multimedia, pp. 6045-6053, 2023. https:\/\/doi.org\/10.1145\/3581783.3612181","DOI":"10.1145\/3581783.3612181"},{"key":"key-10.20965\/jaciii.2026.p0472-8","doi-asserted-by":"crossref","unstructured":"Y. Yu and D. Zhang, \u201cFew-shot multi-modal sentiment analysis with prompt-based vision-aware language modeling,\u201d 2022 IEEE Int. Conf. on Multimedia and Expo, 2022. https:\/\/doi.org\/10.1109\/ICME52920.2022.9859654","DOI":"10.1109\/ICME52920.2022.9859654"},{"key":"key-10.20965\/jaciii.2026.p0472-9","doi-asserted-by":"crossref","unstructured":"Q.-T. Truong and H. W. Lauw, \u201cVistaNet: Visual aspect attention network for multimodal sentiment analysis,\u201d Proc. of the AAAI Conf. on Artificial Intelligence, Vol.33, No.1, pp. 305-312, 2019. https:\/\/doi.org\/10.1609\/aaai.v33i01.3301305","DOI":"10.1609\/aaai.v33i01.3301305"},{"key":"key-10.20965\/jaciii.2026.p0472-10","unstructured":"R. R. Pranesh and A. Shekhar, \u201cMemeSem: A multi-modal framework for sentimental analysis of meme via transfer learning,\u201d 4th Lifelong Learning Machine Workshop at ICML 2020, 2020."},{"key":"key-10.20965\/jaciii.2026.p0472-11","doi-asserted-by":"crossref","unstructured":"H. Cheng, Z. Yang, X. Zhang, and Y. Yang, \u201cMultimodal sentiment analysis based on attentional temporal convolutional network and multi-layer feature fusion,\u201d IEEE Trans. on Affective Computing, Vol.14, No.4, pp. 3149-3163, 2023. https:\/\/doi.org\/10.1109\/TAFFC.2023.3265653","DOI":"10.1109\/TAFFC.2023.3265653"},{"key":"key-10.20965\/jaciii.2026.p0472-12","doi-asserted-by":"crossref","unstructured":"S. Zhou, X. Wu, F. Jiang, Q. Huang, and C. Huang, \u201cEmotion recognition from large-scale video clips with cross-attention and hybrid feature weighting neural networks,\u201d Int. J. of Environmental Research and Public Health, Vol.20, No.2, Article No.1400, 2023. https:\/\/doi.org\/10.3390\/ijerph20021400","DOI":"10.3390\/ijerph20021400"},{"key":"key-10.20965\/jaciii.2026.p0472-13","doi-asserted-by":"crossref","unstructured":"Z. Li, B. Xu, C. Zhu, and T. Zhao, \u201cCLMLF: A contrastive learning and multi-layer fusion method for multimodal sentiment detection,\u201d arXiv:2204.05515, 2022. https:\/\/doi.org\/10.48550\/arXiv.2204.05515","DOI":"10.18653\/v1\/2022.findings-naacl.175"},{"key":"key-10.20965\/jaciii.2026.p0472-14","doi-asserted-by":"crossref","unstructured":"L. P. Hung and S. Alias, \u201cBeyond sentiment analysis: A review of recent trends in text based sentiment analysis and emotion detection,\u201d J. Adv. Comput. Intell. Intell. Inform., Vol.27, No.1, pp. 84-95, 2023. https:\/\/doi.org\/10.20965\/jaciii.2023.p0084","DOI":"10.20965\/jaciii.2023.p0084"},{"key":"key-10.20965\/jaciii.2026.p0472-15","doi-asserted-by":"crossref","unstructured":"A. U. Rehman, A. K. Malik, B. Raza, and W. Ali, \u201cA hybrid CNN-LSTM model for improving accuracy of movie reviews sentiment analysis,\u201d Multimedia Tools and Applications, Vol.78, No.18, pp. 26597-26613, 2019. https:\/\/doi.org\/10.1007\/s11042-019-07788-7","DOI":"10.1007\/s11042-019-07788-7"},{"key":"key-10.20965\/jaciii.2026.p0472-16","doi-asserted-by":"crossref","unstructured":"P. Durga and D. Godavarthi, \u201cDeep-sentiment: An effective deep sentiment analysis using a Decision-based Recurrent Neural Network (D-RNN),\u201d IEEE Access, Vol.11, pp. 108433-108447, 2023. https:\/\/doi.org\/10.1109\/ACCESS.2023.3320738","DOI":"10.1109\/ACCESS.2023.3320738"},{"key":"key-10.20965\/jaciii.2026.p0472-17","doi-asserted-by":"crossref","unstructured":"M. Usama et al., \u201cAttention-based sentiment analysis using convolutional and recurrent neural network,\u201d Future Generation Computer Systems, Vol.113, pp. 571-578, 2020. https:\/\/doi.org\/10.1016\/j.future.2020.07.022","DOI":"10.1016\/j.future.2020.07.022"},{"key":"key-10.20965\/jaciii.2026.p0472-18","doi-asserted-by":"crossref","unstructured":"M. E. Basiri, S. Nemati, M. Abdar, E. Cambria, and U. R. Acharya, \u201cABCDM: An Attention-based Bidirectional CNN-RNN Deep Model for sentiment analysis,\u201d Future Generation Computer Systems, Vol.115, pp. 279-294, 2021. https:\/\/doi.org\/10.1016\/j.future.2020.08.005","DOI":"10.1016\/j.future.2020.08.005"},{"key":"key-10.20965\/jaciii.2026.p0472-19","doi-asserted-by":"crossref","unstructured":"F. Liu et al., \u201cFew-shot adaptation of multi-modal foundation models: A survey,\u201d Artificial Intelligence Review, Vol.57, No.10, Article No.268, 2024. https:\/\/doi.org\/10.1007\/s10462-024-10915-y","DOI":"10.1007\/s10462-024-10915-y"},{"key":"key-10.20965\/jaciii.2026.p0472-20","doi-asserted-by":"crossref","unstructured":"G. Du, H. Wang, X. Xu, Y. Yan, and X. Li, \u201cTCFF-Adapter: Text-driven adaption of CLIP for few-shot image classification,\u201d IEEE Trans. on Circuits and Systems for Video Technology, 2025. https:\/\/doi.org\/10.1109\/TCSVT.2025.3602826","DOI":"10.1109\/TCSVT.2025.3602826"},{"key":"key-10.20965\/jaciii.2026.p0472-21","unstructured":"X. Yu et al., \u201cA survey of few-shot learning on graphs: From meta-learning to pre-training and prompt learning,\u201d arXiv:2402.01440, 2024. https:\/\/doi.org\/10.48550\/arXiv.2402.01440"},{"key":"key-10.20965\/jaciii.2026.p0472-22","doi-asserted-by":"crossref","unstructured":"Y. He, L. Ji, R. Qian, and W. Gu, \u201cA text-based suicide detection model using hybrid prompt tuning in few-shot scenarios,\u201d J. Adv. Comput. Intell. Intell. Inform., Vol.29, No.3, pp. 649-658, 2025. https:\/\/doi.org\/10.20965\/jaciii.2025.p0649","DOI":"10.20965\/jaciii.2025.p0649"},{"key":"key-10.20965\/jaciii.2026.p0472-23","doi-asserted-by":"crossref","unstructured":"H. Dong, W. Zhang, and W. Che, \u201cMetricPrompt: Prompting model as a relevance metric for few-shot text classification,\u201d Proc. of the 29th ACM SIGKDD Conf. on Knowledge Discovery and Data Mining, pp. 426-436, 2023. https:\/\/doi.org\/10.1145\/3580305.3599430","DOI":"10.1145\/3580305.3599430"},{"key":"key-10.20965\/jaciii.2026.p0472-24","unstructured":"E. Hosseini-Asl and W. Liu, \u201cGenerative language model for few-shot aspect-based sentiment analysis,\u201d US Patent 12314673 B2 (Application No.18\/505708), 2024."},{"key":"key-10.20965\/jaciii.2026.p0472-25","unstructured":"M. Tsimpoukelli et al., \u201cMultimodal few-shot learning with frozen language models,\u201d Proc. of the 35th Int. Conf. on Neural Information Processing Systems, pp. 200-212, 2021."},{"key":"key-10.20965\/jaciii.2026.p0472-26","unstructured":"Y. Zang, W. Li, K. Zhou, C. Huang, and C. C. Loy, \u201cUnified vision and language prompt learning,\u201d arXiv:2210.07225, 2022. https:\/\/doi.org\/10.48550\/arXiv.2210.07225"},{"key":"key-10.20965\/jaciii.2026.p0472-27","unstructured":"Z. Zhou, H. Feng, B. Qiao, G. Wu, and D. Han, \u201cSyntax-aware hybrid prompt model for few-shot multi-modal sentiment analysis,\u201d arXiv:2306.01312, 2023. https:\/\/doi.org\/10.48550\/arXiv.2306.01312"},{"key":"key-10.20965\/jaciii.2026.p0472-28","doi-asserted-by":"crossref","unstructured":"E. D. Cubuk, B. Zoph, D. Mane, V. Vasudevan, and Q. V. Le, \u201cAutoAugment: Learning augmentation policies from data,\u201d arXiv:1805.09501, 2018. https:\/\/doi.org\/10.48550\/arXiv.1805.09501","DOI":"10.1109\/CVPR.2019.00020"},{"key":"key-10.20965\/jaciii.2026.p0472-29","doi-asserted-by":"crossref","unstructured":"T. Niu, S. Zhu, L. Pang, and A. El Saddik, \u201cSentiment analysis on multi-view social data,\u201d Proc. of the 22nd Int. Conf. on MultiMedia Modeling, Part 2, pp. 15-27, 2016. https:\/\/doi.org\/10.1007\/978-3-319-27674-8_2","DOI":"10.1007\/978-3-319-27674-8_2"},{"key":"key-10.20965\/jaciii.2026.p0472-30","doi-asserted-by":"crossref","unstructured":"X. Yang, S. Feng, D. Wang, and Y. Zhang, \u201cImage-text multimodal emotion classification via multi-view attentional network,\u201d IEEE Trans. on Multimedia, Vol.23, pp. 4014-4026, 2021. https:\/\/doi.org\/10.1109\/TMM.2020.3035277","DOI":"10.1109\/TMM.2020.3035277"},{"key":"key-10.20965\/jaciii.2026.p0472-31","doi-asserted-by":"crossref","unstructured":"J. Yu and J. Jiang, \u201cAdapting BERT for target-oriented multimodal sentiment classification,\u201d Proc. of the 28th Int. Joint Conf. on Artificial Intelligence, pp. 5408-5414, 2019. https:\/\/doi.org\/10.24963\/ijcai.2019\/751","DOI":"10.24963\/ijcai.2019\/751"},{"key":"key-10.20965\/jaciii.2026.p0472-32","doi-asserted-by":"crossref","unstructured":"J. Zhou, J. Zhao, J. X. Huang, Q. V. Hu, and L. He, \u201cMASAD: A large-scale dataset for multimodal aspect-based sentiment analysis,\u201d Neurocomputing, Vol.455, pp. 47-58, 2021. https:\/\/doi.org\/10.1016\/j.neucom.2021.05.040","DOI":"10.1016\/j.neucom.2021.05.040"},{"key":"key-10.20965\/jaciii.2026.p0472-33","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, \u201cBERT: Pre-training of deep bidirectional transformers for language understanding,\u201d Proc. of the 2019 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol.1, pp. 4171-4186, 2019. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"key-10.20965\/jaciii.2026.p0472-34","unstructured":"T. Gao, A. Fisch, and D. Chen, \u201cMaking pre-trained language models better few-shot learners,\u201d arXiv:2012.15723, 2020. https:\/\/doi.org\/10.48550\/arXiv.2012.15723"},{"key":"key-10.20965\/jaciii.2026.p0472-35","doi-asserted-by":"crossref","unstructured":"J. Yu, J. Jiang, L. Yang, and R. Xia, \u201cImproving multimodal named entity recognition via entity span detection with unified multimodal transformer,\u201d Proc. of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3342-3352, 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.306","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"key-10.20965\/jaciii.2026.p0472-36","doi-asserted-by":"crossref","unstructured":"Z. Khan and Y. Fu, \u201cExploiting BERT for multimodal target sentiment classification through input space translation,\u201d Proc. of the 29th ACM Int. Conf. on Multimedia, pp. 3034-3042, 2021. https:\/\/doi.org\/10.1145\/3474085.3475692","DOI":"10.1145\/3474085.3475692"},{"key":"key-10.20965\/jaciii.2026.p0472-37","doi-asserted-by":"crossref","unstructured":"X. Yang, S. Feng, Y. Zhang, and D. Wang, \u201cMultimodal sentiment detection based on multi-channel graph neural networks,\u201d Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int. Joint Conf. on Natural Language Processing, Vol.1, pp. 328-339, 2021. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.28","DOI":"10.18653\/v1\/2021.acl-long.28"},{"key":"key-10.20965\/jaciii.2026.p0472-38","doi-asserted-by":"crossref","unstructured":"Y. Yu, D. Zhang, and S. Li, \u201cUnified multi-modal pre-training for few-shot sentiment analysis with prompt-based learning,\u201d Proc. of the 30th ACM Int. Conf. on Multimedia, pp. 189-198, 2022. https:\/\/doi.org\/10.1145\/3503161.3548306","DOI":"10.1145\/3503161.3548306"},{"key":"key-10.20965\/jaciii.2026.p0472-39","doi-asserted-by":"crossref","unstructured":"Y. Li, H. Ding, Y. Lin, X. Feng, and L. Chang, \u201cMulti-level textual-visual alignment and fusion network for multimodal aspect-based sentiment analysis,\u201d Artificial Intelligence Review, Vol.57, No.4, Article No.78, 2024. https:\/\/doi.org\/10.1007\/s10462-023-10685-z","DOI":"10.1007\/s10462-023-10685-z"}],"container-title":["Journal of Advanced Computational Intelligence and Intelligent Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.fujipress.jp\/main\/wp-content\/themes\/Fujipress\/hyosetsu.php?ppno=jacii003000020015","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T15:04:25Z","timestamp":1773932665000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.fujipress.jp\/jaciii\/jc\/jacii003000020472"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":39,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,3,20]]},"published-print":{"date-parts":[[2026,3,20]]}},"URL":"https:\/\/doi.org\/10.20965\/jaciii.2026.p0472","relation":{},"ISSN":["1883-8014","1343-0130"],"issn-type":[{"value":"1883-8014","type":"electronic"},{"value":"1343-0130","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,20]]}}}