{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T05:07:50Z","timestamp":1778648870328,"version":"3.51.4"},"reference-count":40,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T00:00:00Z","timestamp":1777766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MTI"],"abstract":"<jats:p>Despite significant advances, multimodal sentiment analysis still faces critical challenges in modeling complex cross-modal interactions and extracting discriminative sentiment features. To address these limitations, this paper proposes a hierarchical multimodal sentiment analysis framework. Specifically, a cross-modal feature enhancement module is first introduced to capture deep correlations among textual, visual, and acoustic modalities via cross-attention mechanisms, thereby obtaining context-aware fused representations. Subsequently, an attention-gated feature disentanglement approach is employed to effectively separate sentiment-relevant information from content-specific features within the fused representations; an independence loss is further imposed to enforce orthogonality between these two feature subsets, thereby mitigating noise induced by repetitive visual frames and textual stop words. Finally, all disentangled features are integrated to facilitate high-level sentiment reasoning through a multimodal logical inference module, where supervised contrastive loss is incorporated to enhance the discriminability of sentiment expressions. Extensive experiments conducted on two public benchmarks, CMU-MOSI and CMU-MOSEI, demonstrate that the proposed framework achieves improvements of 2\u20136% across multiple evaluation metrics compared with state-of-the-art methods.<\/jats:p>","DOI":"10.3390\/mti10050050","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T02:06:21Z","timestamp":1777860381000},"page":"50","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sentiment Analysis Based on Enhanced Feature Decoupling and Multimodal Logical Reasoning"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2327-3211","authenticated-orcid":false,"given":"Hua","family":"Yang","sequence":"first","affiliation":[{"name":"School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2569-8698","authenticated-orcid":false,"given":"Ming","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanhao","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junying","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziran","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baozhou","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingzhe","family":"He","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3586075","article-title":"Multimodal sentiment analysis: A survey of methods, trends, and challenges","volume":"55","author":"Das","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Yang, X., Feng, S., Wang, D., Zhang, Y., and Poria, S. (2023). Few-shot multimodal sentiment analysis based on multimodal probabilistic fusion prompts. Proceedings of the 31st ACM International Conference on Multimedia, ACM.","DOI":"10.1145\/3581783.3612181"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"127006","DOI":"10.1016\/j.energy.2023.127006","article-title":"Time- varying interval prediction and decision-making for short-term wind power using convolutional gated recurrent unit and multi-objective elephant clan optimization","volume":"271","author":"Zhu","year":"2023","journal-title":"Energy"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"0076","DOI":"10.34133\/icomputing.0076","article-title":"Affective computing: Recent advances, challenges, and future trends","volume":"3","author":"Pei","year":"2024","journal-title":"Intell. Comput."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Paw\u0142owski, M., Wr\u00f3blewska, A., and Sysko-Roma\u0144czuk, S. (2023). Effective techniques for multimodal data fusion: A comparative analysis. Sensors, 23.","DOI":"10.3390\/s23052381"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"109602","DOI":"10.1016\/j.asoc.2022.109602","article-title":"Clustering-based interval prediction of electric load using multi-objective pathfinder algorithm and Elman neural network","volume":"129","author":"Jiang","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"ref_7","unstructured":"Zhang, Q., Wei, Y., Han, Z., Fu, H., Peng, X., Deng, C., Hu, Q., Xu, C., Wen, J., and Hu, D. (2024). Multimodal fusion on low-quality data: A comprehensive survey. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"5731","DOI":"10.1007\/s10462-022-10144-1","article-title":"A survey on sentiment analysis methods, applications, and challenges","volume":"55","author":"Wankhade","year":"2022","journal-title":"Artif. Intell. Rev."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., and Morency, L.P. (2017). Tensor fusion network for multimodal sentiment analysis. arXiv.","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Li, T., Zhang, L., Liu, S., and Shen, S. (2024). Multi-modal integrated prediction and decision-making with adaptive interaction modality explorations. arXiv.","DOI":"10.1109\/IROS60139.2025.11247130"},{"key":"ref_11","first-page":"423","article-title":"Multimodal machine learning: A survey and taxonomy","volume":"41","author":"Ahuja","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wang, Y., Albrecht, C.M., Braham, N.A.A., Liu, C., Xiong, Z., and Zhu, X.X. (2024). Decoupling common and unique representations for multimodal self-supervised learning. Proceedings of the European Conference on Computer Vision, Springer Nature.","DOI":"10.1007\/978-3-031-73397-0_17"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Han, W., Chen, H., and Poria, S. (2021). Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. Proceedings of the 2021 Conference on Empirical Methods in Natural, ACL.","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wu, S.X., Dai, D.M., Qin, Z.W., Liu, T.Y., Lin, B., Cao, Y.B., and Sui, Z.F. (2023). Denoising bottleneck with mutual information maximization for video multimodal fusion. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, ACL.","DOI":"10.18653\/v1\/2023.acl-long.124"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Yin, G., Liu, K., Liu, Y., and Yu, T. (2023). Learning language-guided adaptive hyper-modality representation for multimodal sentiment analysis. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, ACL.","DOI":"10.18653\/v1\/2023.emnlp-main.49"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yang, H., Zhang, S., Shen, H., Zhang, G., Deng, X., Xiong, J., Feng, L., Wang, J., Zhang, H., and Sheng, S. (2023). A multi-layer feature fusion model based on convolution and attention mechanisms for text classification. Appl. Sci., 13.","DOI":"10.3390\/app13148550"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"7675","DOI":"10.1007\/s00521-024-10011-w","article-title":"A study of progressive data flow knowledge tracing based on reconstructed attention mechanism","volume":"37","author":"Wu","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Singh, P., and Raman, B. (2025). Transformer Architecture: Encoder and Decoder. The Geometry of Intelligence: Foundations of Transformer Networks in Deep Learning, Springer Nature.","DOI":"10.1007\/978-981-96-4706-4_4"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Lu, W., Chen, S.B., Shu, Q.L., Tang, J., and Luo, B. (2024). Decouplenet: A lightweight backbone network with efficient feature decoupling for remote sensing visual tasks. IEEE Trans. Geosci. Remote Sens., 62.","DOI":"10.1109\/TGRS.2024.3465496"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, X., Cao, L., Huang, W., Sun, F., and Wang, Y. (2022). Multimodal token fusion for vision transformers. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref_21","first-page":"1","article-title":"Foundations trends in multimodal machine learning: Principles, challenges, and open questions","volume":"56","author":"Liang","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"ref_22","first-page":"405","article-title":"A multimodal fusion method for semantic segmentation of high-resolution remote sensing images","volume":"39","author":"Li","year":"2020","journal-title":"J. South-Cent. Univ. Natl. (Nat. Sci. Ed.)"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1385","DOI":"10.1007\/s11042-024-19152-5","article-title":"Transformer- based adaptive contrastive learning for multimodal sentiment analysis","volume":"84","author":"Hu","year":"2025","journal-title":"Multimed. Tools Appl."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"4105","DOI":"10.1109\/TASLP.2024.3458812","article-title":"Trisat: Trimodal representation learning for multimodal sentiment analysis","volume":"32","author":"Huan","year":"2024","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_25","unstructured":"Zadeh, A., Zellers, R., Pincus, E., and Morency, L.P. (2016). MOSI: Multimodal corpus of sentiment intensity and subjectivity analysis in online opinion video. arXiv."},{"key":"ref_26","unstructured":"Zadeh, A.A.B., Liang, P.P., Poria, S., Cambria, E., and Morency, L.P. (2018). Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL."},{"key":"ref_27","unstructured":"Tsai, Y.H.H., Liang, P.P., Zadeh, A., Morency, L.P., and Salakhutdinov, R. (2018). Learning factorized multimodal representations. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.P., and Salakhutdinov, R. (2019). Multimodal transformer for unaligned multimodal language sequences. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, ACL.","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Zimmermann, R., and Poria, S. (2020). Misa: Modality-invariant and-specific representations for multimodal sentiment analysis. Proceedings of the 28th ACM International Conference on Multimedia, ACM.","DOI":"10.1145\/3394171.3413678"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wu, J., Mai, S., and Hu, H. (2021). Graph capsule aggregation for unaligned multimodal sequences. Proceedings of the 2021 International Conference on Multimodal Interaction, ACM.","DOI":"10.1145\/3462244.3479931"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.neucom.2021.09.041","article-title":"Multimodal sentiment analysis with unidirectional modality translation","volume":"467","author":"Yang","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"109259","DOI":"10.1016\/j.patcog.2022.109259","article-title":"TETFN: A text enhanced transformer fusion network for multimodal sentiment analysis","volume":"136","author":"Wang","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Lei, Y., Yang, D., Li, M., Wang, S., Chen, J., and Zhang, L. (2023). Text-oriented modality reinforcement network for multimodal sentiment analysis from unaligned multimodal sequences. Proceedings of the CAAI International Conference on Artificial Intelligence, Springer Nature.","DOI":"10.1007\/978-981-99-9119-8_18"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"107335","DOI":"10.1016\/j.engappai.2023.107335","article-title":"A feature-based restoration dynamic interaction network for multimodal sentiment analysis","volume":"127","author":"Zeng","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"111149","DOI":"10.1016\/j.knosys.2023.111149","article-title":"Co-space representation interaction network for multimodal sentiment analysis","volume":"283","author":"Shi","year":"2024","journal-title":"Knowl. Based Syst."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Ma, G., Ren, X., Jiang, Y., Guan, H., and Xu, B. (2025). From Feature Alignment to Multimodal Fusion: A Two-Stage Primary Modality-Guided Approach for MSA. Proceedings of the 7th ACM International Conference on Multimedia in Asia, ACM.","DOI":"10.1145\/3743093.3771041"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Wang, Q., Xia, W., Tao, Z., Gao, Q., and Cao, X. (2021). Deep self- supervised t-SNE for multi-modal subspace clustering. Proceedings of the 29th ACM International Conference on Multimedia, ACM.","DOI":"10.1145\/3474085.3475319"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"32265","DOI":"10.1007\/s11042-022-13091-9","article-title":"A multimodal emotion recognition model integrating speech, video and MoCAP","volume":"81","author":"Jia","year":"2022","journal-title":"Multimed. Tools Appl."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Kumar, H., Aruldoss, M., and Wynn, M. (2025). Cross-Modal Attention Fusion: A Deep Learning and Affective Computing Model for Emotion Recognition. Multimodal Technol. Interact., 9.","DOI":"10.3390\/mti9120116"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Wang, Z., Luo, Y., Qiu, R., Huang, Z., and Baktashmotlagh, M. (2021). Learning to diversify for single domain generalization. Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV48922.2021.00087"}],"container-title":["Multimodal Technologies and Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2414-4088\/10\/5\/50\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T04:11:48Z","timestamp":1778645508000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2414-4088\/10\/5\/50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,3]]},"references-count":40,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["mti10050050"],"URL":"https:\/\/doi.org\/10.3390\/mti10050050","relation":{},"ISSN":["2414-4088"],"issn-type":[{"value":"2414-4088","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,3]]}}}