{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T12:47:23Z","timestamp":1782132443325,"version":"3.54.5"},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.inffus.2026.104491","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T15:22:49Z","timestamp":1779204169000},"page":"104491","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Internalizing reasoning via chain-of-thought and retrieval augmentation for multimodal sentiment analysis"],"prefix":"10.1016","volume":"135","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0913-5757","authenticated-orcid":false,"given":"Yang","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3432-6215","authenticated-orcid":false,"given":"Fengling","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8013-5188","authenticated-orcid":false,"given":"Tianshi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1076-2119","authenticated-orcid":false,"given":"Guoli","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3827-1960","authenticated-orcid":false,"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104491_bib0001","series-title":"Conference on Empirical Methods in Natural Language Processing","first-page":"1103","article-title":"Tensor fusion network for multimodal sentiment analysis","author":"Zadeh","year":"2017"},{"key":"10.1016\/j.inffus.2026.104491_bib0002","series-title":"Annual Meeting of the Association for Computational Linguistics","first-page":"6558","article-title":"Multimodal transformer for unaligned multimodal language sequences","author":"Tsai","year":"2019"},{"key":"10.1016\/j.inffus.2026.104491_bib0003","doi-asserted-by":"crossref","first-page":"4014","DOI":"10.1109\/TMM.2020.3035277","article-title":"Image-text multimodal emotion classification via multi-view attentional network","volume":"23","author":"Yang","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104491_bib0004","doi-asserted-by":"crossref","first-page":"5753","DOI":"10.1109\/TMM.2023.3338769","article-title":"UniMF: a unified multimodal framework for multimodal sentiment analysis in missing modalities and unaligned multimodal sequences","volume":"26","author":"Huan","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104491_bib0005","series-title":"Annual Meeting of the Association for Computational Linguistics","first-page":"2359","article-title":"Integrating multimodal information in large pretrained transformers","author":"Rahman","year":"2020"},{"issue":"1","key":"10.1016\/j.inffus.2026.104491_bib0006","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1109\/TAFFC.2023.3274829","article-title":"Efficient multimodal transformer with dual-Level feature restoration for robust multimodal sentiment analysis","volume":"15","author":"Sun","year":"2024","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.inffus.2026.104491_bib0007","series-title":"International Joint Conference on Artificial Intelligence","first-page":"5408","article-title":"Adapting BERT for target-Oriented multimodal sentiment classification","author":"Yu","year":"2019"},{"key":"10.1016\/j.inffus.2026.104491_bib0008","series-title":"Annual Meeting of the Association for Computational Linguistics","first-page":"2149","article-title":"Vision-language pre-Training for multimodal aspect-based sentiment analysis","author":"Ling","year":"2022"},{"issue":"3","key":"10.1016\/j.inffus.2026.104491_bib0009","doi-asserted-by":"crossref","first-page":"1966","DOI":"10.1109\/TAFFC.2022.3171091","article-title":"Hierarchical interactive multimodal transformer for aspect-Based multimodal sentiment analysis","volume":"14","author":"Yu","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"3","key":"10.1016\/j.inffus.2026.104491_bib0010","doi-asserted-by":"crossref","first-page":"2074","DOI":"10.1109\/TCSVT.2024.3490665","article-title":"Collaborative aware bidirectional semantic reasoning for video question answering","volume":"35","author":"Wu","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.inffus.2026.104491_bib0011","unstructured":"S. Bai, Y. Cai, R. Chen, K. Chen, X. Chen, Z. Cheng, L. Deng, W. Ding, C. Gao, C. Ge, W. Ge, Z. Guo, Q. Huang, J. Huang, F. Huang, B. Hui, S. Jiang, Z. Li, M. Li, M. Li, K. Li, Z. Lin, J. Lin, X. Liu, J. Liu, C. Liu, Y. Liu, D. Liu, S. Liu, D. Lu, R. Luo, C. Lv, R. Men, L. Meng, X. Ren, X. Ren, S. Song, Y. Sun, J. Tang, J. Tu, J. Wan, P. Wang, P. Wang, Q. Wang, Y. Wang, T. Xie, Y. Xu, H. Xu, J. Xu, Z. Yang, M. Yang, J. Yang, A. Yang, B. Yu, F. Zhang, H. Zhang, X. Zhang, B. Zheng, H. Zhong, J. Zhou, F. Zhou, J. Zhou, Y. Zhu, K. Zhu, Qwen3-VL Technical Report, arXiv Prepr. arXiv abs\/2511.21631 (2025)."},{"key":"10.1016\/j.inffus.2026.104491_bib0012","unstructured":"W. Wang, Z. Gao, L. Gu, H. Pu, L. Cui, X. Wei, Z. Liu, L. Jing, S. Ye, J. Shao, Z. Wang, Z. Chen, H. Zhang, G. Yang, H. Wang, Q. Wei, J. Yin, W. Li, E. Cui, G. Chen, Z. Ding, C. Tian, Z. Wu, J. Xie, Z. Li, B. Yang, Y. Duan, X. Wang, Z. Hou, H. Hao, T. Zhang, S. Li, X. Zhao, H. Duan, N. Deng, B. Fu, Y. He, Y. Wang, C. He, B. Shi, J. He, Y. Xiong, H. Lv, L. Wu, W. Shao, K. Zhang, H. Deng, B. Qi, J. Ge, Q. Guo, W. Zhang, S. Zhang, M. Cao, J. Lin, K. Tang, J. Gao, H. Huang, Y. Gu, C. Lyu, H. Tang, R. Wang, H. Lv, W. Ouyang, L. Wang, M. Dou, X. Zhu, T. Lu, D. Lin, J. Dai, W. Su, B. Zhou, K. Chen, Y. Qiao, W. Wang, G. Luo, InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency, arXiv Prepr. arXiv abs\/2508.18265 (2025)."},{"key":"10.1016\/j.inffus.2026.104491_bib0013","series-title":"Annual Meeting of the Association for Computational Linguistics","first-page":"2247","article-title":"Efficient low-rank multimodal fusion with modality-Specific factors","author":"Liu","year":"2018"},{"key":"10.1016\/j.inffus.2026.104491_bib0014","series-title":"ACM International Conference on Multimedia","first-page":"1122","article-title":"MISA: Modality-Invariant and -Specific representations for multimodal sentiment analysis","author":"Hazarika","year":"2020"},{"key":"10.1016\/j.inffus.2026.104491_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102725","article-title":"AtCAF: attention-based causality-aware fusion network for multimodal sentiment analysis","volume":"114","author":"Huang","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104491_bib0016","series-title":"Conference on Empirical Methods in Natural Language Processing","first-page":"4395","article-title":"Joint multi-modal aspect-Sentiment analysis with auxiliary cross-modal relation detection","author":"Ju","year":"2021"},{"key":"10.1016\/j.inffus.2026.104491_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101847","article-title":"Emotion recognition from unimodal to multimodal analysis: a review","volume":"99","author":"Ezzameli","year":"2023","journal-title":"Inf. Fusion"},{"issue":"6","key":"10.1016\/j.inffus.2026.104491_bib0018","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1109\/MSP.2021.3106895","article-title":"Emotion recognition from multiple modalities: fundamentals and methodologies","volume":"38","author":"Zhao","year":"2021","journal-title":"IEEE Signal Process. Mag."},{"key":"10.1016\/j.inffus.2026.104491_bib0019","series-title":"AAAI Conference on Artificial Intelligence","first-page":"5642","article-title":"Multi-attention recurrent network for human communication comprehension","author":"Zadeh","year":"2018"},{"key":"10.1016\/j.inffus.2026.104491_bib0020","doi-asserted-by":"crossref","first-page":"4909","DOI":"10.1109\/TMM.2022.3183830","article-title":"Cross-Modal enhancement network for multimodal sentiment analysis","volume":"25","author":"Wang","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104491_bib0021","doi-asserted-by":"crossref","first-page":"2740","DOI":"10.1109\/TMM.2023.3303711","article-title":"Dynamically shifting multimodal representations via hybrid-Modal attention for multimodal sentiment analysis","volume":"26","author":"Lin","year":"2024","journal-title":"IEEE Trans. Multimed."},{"issue":"3","key":"10.1016\/j.inffus.2026.104491_bib0022","doi-asserted-by":"crossref","first-page":"1802","DOI":"10.1109\/TAFFC.2025.3539225","article-title":"SDRS: Sentiment-aware disentangled representation shifting for multimodal sentiment analysis","volume":"16","author":"Zhao","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.inffus.2026.104491_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103058","article-title":"SSLMM: Semi-supervised learning with missing modalities for multimodal sentiment analysis","volume":"120","author":"Wang","year":"2025","journal-title":"Inf. Fusion"},{"issue":"8","key":"10.1016\/j.inffus.2026.104491_bib0024","doi-asserted-by":"crossref","first-page":"7657","DOI":"10.1109\/TCSVT.2024.3376564","article-title":"Trustworthy multimodal fusion for sentiment analysis in ordinal sentiment space","volume":"34","author":"Xie","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"10","key":"10.1016\/j.inffus.2026.104491_bib0025","doi-asserted-by":"crossref","first-page":"5886","DOI":"10.1109\/TFUZZ.2024.3434614","article-title":"A multimodal sentiment analysis method based on fuzzy attention fusion","volume":"32","author":"Zhi","year":"2024","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"10.1016\/j.inffus.2026.104491_bib0026","series-title":"ACM International Conference on Multimedia","first-page":"3034","article-title":"Exploiting BERT for multimodal target sentiment classification through input space translation","author":"Khan","year":"2021"},{"key":"10.1016\/j.inffus.2026.104491_bib0027","series-title":"Conference on Neural Information Processing Systems","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022"},{"key":"10.1016\/j.inffus.2026.104491_bib0028","series-title":"International Conference on Learning Representations","article-title":"Self-Consistency improves chain of thought reasoning in language models","author":"Wang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104491_bib0029","series-title":"Conference on Neural Information Processing Systems","article-title":"Tree of thoughts: deliberate problem solving with large language models","author":"Yao","year":"2023"},{"key":"10.1016\/j.inffus.2026.104491_bib0030","series-title":"Conference on Neural Information Processing Systems","article-title":"STaR: bootstrapping reasoning with reasoning","author":"Zelikman","year":"2022"},{"key":"10.1016\/j.inffus.2026.104491_bib0031","series-title":"Findings of the Association for Computational Linguistics","first-page":"8003","article-title":"Distilling step-by-Step! outperforming larger language models with less training data and smaller model sizes","author":"Hsieh","year":"2023"},{"key":"10.1016\/j.inffus.2026.104491_bib0032","series-title":"Conference on Neural Information Processing Systems","article-title":"Learn to explain: multimodal reasoning via thought chains for science question answering","author":"Lu","year":"2022"},{"key":"10.1016\/j.inffus.2026.104491_bib0033","article-title":"Multimodal chain-of-Thought reasoning in language models","volume":"2024","author":"Zhang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.inffus.2026.104491_bib0034","first-page":"1","article-title":"SCL: Semantic coherence learning for video question answering","author":"Wu","year":"2026","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104491_bib0035","series-title":"Conference on Neural Information Processing Systems","article-title":"Language models Don\u2019t always say what they think: unfaithful explanations in chain-of-Thought prompting","author":"Turpin","year":"2023"},{"key":"10.1016\/j.inffus.2026.104491_bib0036","series-title":"International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","first-page":"305","article-title":"Faithful chain-of-Thought reasoning","author":"Lyu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104491_bib0037","series-title":"Conference on Neural Information Processing Systems","article-title":"Language models are few-Shot learners","author":"Brown","year":"2020"},{"key":"10.1016\/j.inffus.2026.104491_bib0038","series-title":"Conference on Empirical Methods in Natural Language Processing","first-page":"11048","article-title":"Rethinking the role of demonstrations: what makes in-Context learning work?","author":"Min","year":"2022"},{"key":"10.1016\/j.inffus.2026.104491_bib0039","series-title":"Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"2300","article-title":"Do prompt-based models really understand the meaning of their prompts?","author":"Webson","year":"2022"},{"key":"10.1016\/j.inffus.2026.104491_bib0040","series-title":"International Conference on Learning Representations","article-title":"An explanation of in-context learning as implicit bayesian inference","author":"Xie","year":"2022"},{"key":"10.1016\/j.inffus.2026.104491_bib0041","series-title":"International Conference on Machine Learning","first-page":"35151","article-title":"Transformers learn in-Context by gradient descent","volume":"202","author":"von Oswald","year":"2023"},{"key":"10.1016\/j.inffus.2026.104491_bib0042","series-title":"Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"2655","article-title":"Learning to retrieve prompts for in-Context learning","author":"Rubin","year":"2022"},{"key":"10.1016\/j.inffus.2026.104491_bib0043","series-title":"International Conference on Machine Learning","first-page":"12697","article-title":"Calibrate before use: improving few-shot performance of language models","volume":"139","author":"Zhao","year":"2021"},{"issue":"11","key":"10.1016\/j.inffus.2026.104491_bib0044","doi-asserted-by":"crossref","first-page":"1716","DOI":"10.1109\/JPROC.2024.3525147","article-title":"Cross-modal retrieval: a systematic review of methods and future directions","volume":"112","author":"Wang","year":"2024","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.inffus.2026.104491_bib0045","unstructured":"H.J. Kim, H. Cho, J. Kim, T. Kim, K.M. Yoo, S. Lee, Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator, arXiv Prepr. arXiv abs\/2206.08082 (2022)."},{"key":"10.1016\/j.inffus.2026.104491_bib0046","series-title":"Conference on Empirical Methods in Natural Language Processing","first-page":"15651","article-title":"Self-ICL: zero-Shot in-Context learning with self-Generated demonstrations","author":"Chen","year":"2023"},{"key":"10.1016\/j.inffus.2026.104491_bib0047","series-title":"Conference on Neural Information Processing Systems","article-title":"Flamingo: a visual language model for few-Shot learning","author":"Alayrac","year":"2022"},{"key":"10.1016\/j.inffus.2026.104491_bib0048","series-title":"Findings of the Association for Computational Linguistics","first-page":"11575","article-title":"Few-shot joint multimodal aspect-Sentiment analysis based on generative multimodal prompt","author":"Yang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104491_bib0049","series-title":"International Conference on Multimedia Modeling","first-page":"15","article-title":"Sentiment analysis on multi-View social data","volume":"9517","author":"Niu","year":"2016"},{"key":"10.1016\/j.inffus.2026.104491_bib0050","series-title":"ACM International Conference on Information and Knowledge Management","first-page":"2399","article-title":"Multisentinet: a deep semantic network for multimodal sentiment analysis","author":"Xu","year":"2017"},{"key":"10.1016\/j.inffus.2026.104491_bib0051","series-title":"AAAI Conference on Artificial Intelligence","first-page":"5674","article-title":"Adaptive co-attention network for named entity recognition in tweets","author":"Zhang","year":"2018"},{"key":"10.1016\/j.inffus.2026.104491_bib0052","series-title":"Annual Meeting of the Association for Computational Linguistics","first-page":"1990","article-title":"Visual attention model for name tagging in multimodal social media","author":"Lu","year":"2018"},{"key":"10.1016\/j.inffus.2026.104491_bib0053","unstructured":"A. Marafioti, O. Zohar, M. Farr\u00e9, M. Noyan, E. Bakouch, P. Cuenca, C. Zakka, L.B. Allal, A. Lozhkov, N. Tazi, V. Srivastav, J. Lochner, H. Larcher, M. Morlon, L. Tunstall, L. von Werra, T. Wolf, SmolVLM: Redefining small and efficient multimodal models, arXiv Prepr. arXiv abs\/2504.05299 (2025)."},{"key":"10.1016\/j.inffus.2026.104491_bib0054","unstructured":"A. Steiner, A.S. Pinto, M. Tschannen, D. Keysers, X. Wang, Y. Bitton, A.A. Gritsenko, M. Minderer, A. Sherbondy, S. Long, S. Qin, R.R. Ingle, E. Bugliarello, S. Kazemzadeh, T. Mesnard, I. Alabdulmohsin, L. Beyer, X. Zhai, PaliGemma 2: A Family of Versatile VLMs for Transfer, arXiv Prepr. arXiv abs\/2412.03555 (2024)."},{"key":"10.1016\/j.inffus.2026.104491_bib0055","unstructured":"W. Yin, Y. Ye, F. Shu, Y. Liao, Z. Kang, H. Dong, H. Yu, D. Yang, J. Wang, H. Wang, W. Liu, X. Liang, S. Yan, C. Feng, SAIL-VL2 Technical Report, arXiv Prepr. arXiv abs\/2509.14033 (2025)."},{"key":"10.1016\/j.inffus.2026.104491_bib0056","series-title":"IEEE\/CVF International Conference on Computer Vision","first-page":"11941","article-title":"Sigmoid loss for language image pre-Training","author":"Zhai","year":"2023"},{"issue":"3","key":"10.1016\/j.inffus.2026.104491_bib0057","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","article-title":"Billion-Scale similarity search with GPUs","volume":"7","author":"Johnson","year":"2021","journal-title":"IEEE Trans. Big Data"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003702?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003702?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T11:49:25Z","timestamp":1782128965000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526003702"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":57,"alternative-id":["S1566253526003702"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104491","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Internalizing reasoning via chain-of-thought and retrieval augmentation for multimodal sentiment analysis","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104491","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104491"}}