{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T17:07:34Z","timestamp":1774026454104,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T00:00:00Z","timestamp":1741219200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T00:00:00Z","timestamp":1741219200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"DOI":"10.1007\/s11063-025-11737-x","type":"journal-article","created":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T00:14:07Z","timestamp":1741220047000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Multimodal Aspect-Based Sentiment Analysis with External Knowledge and Multi-granularity Image-Text Features"],"prefix":"10.1007","volume":"57","author":[{"given":"Zhanghui","family":"Liu","sequence":"first","affiliation":[]},{"given":"Jiali","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Yuzhong","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Dong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,6]]},"reference":[{"key":"11737_CR1","doi-asserted-by":"publisher","unstructured":"Ju X, Zhang D, Xiao R, Li J, Li S, Zhang M, Zhou G (2021) Joint multi-modal aspect-sentiment analysis with auxiliary cross-modal relation detection. In: Proceedings of the 2021 conference on empirical methods in natural language processing, pp 4395\u20134405. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.360","DOI":"10.18653\/v1\/2021.emnlp-main.360"},{"key":"11737_CR2","doi-asserted-by":"publisher","unstructured":"Zhang Q, Fu J, Liu X, Huang X (2018) Adaptive co-attention network for named entity recognition in tweets. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 32. https:\/\/doi.org\/10.1609\/aaai.v32i1.11962","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"11737_CR3","doi-asserted-by":"publisher","unstructured":"Sun L, Wang J, Zhang K, Su Y, Weng F (2021) Rpbert: a text-image relation propagation-based bert model for multimodal ner. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 13860\u201313868. https:\/\/doi.org\/10.1609\/aaai.v35i15.17633","DOI":"10.1609\/aaai.v35i15.17633"},{"key":"11737_CR4","doi-asserted-by":"publisher","unstructured":"Xu N, Mao W, Chen G (2019) Multi-interactive memory network for aspect based multimodal sentiment analysis. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 371\u2013378. https:\/\/doi.org\/10.1609\/aaai.v33i01.3301371","DOI":"10.1609\/aaai.v33i01.3301371"},{"key":"11737_CR5","unstructured":"Zhao F, Wu Z, Long S, Dai X, Huang S, Chen J (2022) Learning from adjective-noun pairs: a knowledge-enhanced framework for target-oriented multimodal sentiment classification. In: Proceedings of the 29th international conference on computational linguistics, pp 6784\u20136794"},{"key":"11737_CR6","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the north american chapter of the association for computational linguistics: human language technologies, vol 1 (Long and Short Papers), pp 4171\u20134186. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"11737_CR7","doi-asserted-by":"publisher","unstructured":"Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L (2020) Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 7871\u20137880. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"11737_CR8","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"11737_CR9","doi-asserted-by":"crossref","unstructured":"Anderson P, He X, Buehler C, Teney D, Johnson M, Gould S, Zhang L (2018) Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6077\u20136086","DOI":"10.1109\/CVPR.2018.00636"},{"issue":"5","key":"11737_CR10","doi-asserted-by":"publisher","first-page":"103038","DOI":"10.1016\/j.ipm.2022.103038","volume":"59","author":"L Yang","year":"2022","unstructured":"Yang L, Na J-C, Yu J (2022) Cross-modal multitask transformer for end-to-end multimodal aspect-based sentiment analysis. Inf Process Manag 59(5):103038. https:\/\/doi.org\/10.1016\/j.ipm.2022.103038","journal-title":"Inf Process Manag"},{"key":"11737_CR11","doi-asserted-by":"publisher","unstructured":"Ling Y, Yu J, Xia R (2022) Vision-language pre-training for multimodal aspect-based sentiment analysis. In: Proceedings of the 60th annual meeting of the association for computational linguistics, vol 1: Long Papers, pp 2149\u20132159. https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.152","DOI":"10.18653\/v1\/2022.acl-long.152"},{"key":"11737_CR12","doi-asserted-by":"publisher","unstructured":"Zhou R, Guo W, Liu X, Yu S, Zhang Y, Yuan X (2023) Aom: detecting aspect-oriented information for multimodal aspect-based sentiment analysis. In: Findings of the association for computational linguistics: ACL 2023, pp 8184\u20138196. https:\/\/doi.org\/10.18653\/v1\/2023.findings-acl.519","DOI":"10.18653\/v1\/2023.findings-acl.519"},{"key":"11737_CR13","doi-asserted-by":"publisher","unstructured":"Zhao F, Li C, Wu Z, Ouyang Y, Zhang J, Dai X (2023) M2df: Multi-grained multi-curriculum denoising framework for multimodal aspect-based sentiment analysis. In: Proceedings of the 2023 conference on empirical methods in natural language processing, pp 9057\u20139070. https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.561","DOI":"10.18653\/v1\/2023.emnlp-main.561"},{"key":"11737_CR14","doi-asserted-by":"crossref","unstructured":"Yu J, Jiang J (2019) Adapting bert for target-oriented multimodal sentiment classification. In: Proceedings of the twenty-eighth international joint conference on artificial intelligence, pp 5408\u20135414","DOI":"10.24963\/ijcai.2019\/751"},{"key":"11737_CR15","doi-asserted-by":"publisher","unstructured":"Chen G, Tian Y, Song Y (2020) Joint aspect extraction and sentiment analysis with directional graph convolutional networks. In: Proceedings of the 28th international conference on computational linguistics, pp 272\u2013279. https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.24","DOI":"10.18653\/v1\/2020.coling-main.24"},{"key":"11737_CR16","doi-asserted-by":"publisher","unstructured":"Zhang C, Li Q, Song D (2019) Aspect-based sentiment classification with aspect-specific graph convolutional networks. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 4568\u20134578. https:\/\/doi.org\/10.18653\/v1\/D19-1464","DOI":"10.18653\/v1\/D19-1464"},{"key":"11737_CR17","doi-asserted-by":"publisher","unstructured":"Xu Z, Su Q, Xiao J (2023) Multimodal aspect-based sentiment classification with knowledge-injected transformer. In: 2023 IEEE international conference on multimedia and expo (ICME), pp 1379\u20131384. https:\/\/doi.org\/10.1109\/ICME55011.2023.00239 . IEEE","DOI":"10.1109\/ICME55011.2023.00239"},{"key":"11737_CR18","doi-asserted-by":"publisher","unstructured":"Khan Z, Fu Y (2021) Exploiting bert for multimodal target sentiment classification through input space translation. In: Proceedings of the 29th ACM international conference on multimedia, pp 3034\u20133042. https:\/\/doi.org\/10.1145\/3474085.347569","DOI":"10.1145\/3474085.347569"},{"key":"11737_CR19","doi-asserted-by":"crossref","unstructured":"Chen Y-C, Li L, Yu L, El\u00a0Kholy A, Ahmed F, Gan Z, Cheng Y, Liu J (2020) Uniter: universal image-text representation learning. In: European conference on computer vision. Springer, pp 104\u2013120","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"11737_CR20","doi-asserted-by":"publisher","unstructured":"Li X, Yin X, Li C, Zhang P, Hu X, Zhang L, Wang L, Hu H, Dong L, Wei F et al (2020) Oscar: object-semantics aligned pre-training for vision-language tasks. In: Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, Part XXX 16. Springer, pp 121\u2013137. https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"11737_CR21","doi-asserted-by":"publisher","unstructured":"Li X, Bing L, Li P, Lam W (2019) A unified model for opinion target extraction and target sentiment prediction. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 6714\u20136721. https:\/\/doi.org\/10.1609\/aaai.v33i01.33016714","DOI":"10.1609\/aaai.v33i01.33016714"},{"key":"11737_CR22","doi-asserted-by":"publisher","unstructured":"Chen Z, Qian T (2020) Enhancing aspect term extraction with soft prototypes. In: Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP), pp 2107\u20132117. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.164","DOI":"10.18653\/v1\/2020.emnlp-main.164"},{"key":"11737_CR23","unstructured":"Tang D, Qin B, Feng X, Liu T (2016) Effective lstms for target-dependent sentiment classification. In: Proceedings of COLING 2016, the 26th international conference on computational linguistics: technical papers, pp 3298\u20133307"},{"key":"11737_CR24","doi-asserted-by":"publisher","unstructured":"Ma F, Hu X, Liu A, Yang Y, Li S, Yu PS, Wen L (2023) Amr-based network for aspect-based sentiment analysis. In: Proceedings of the 61st annual meeting of the association for computational linguistics, vol 1: Long Papers, pp 322\u2013337. https:\/\/doi.org\/10.18653\/V1\/2023.ACL-LONG.19","DOI":"10.18653\/V1\/2023.ACL-LONG.19"},{"key":"11737_CR25","doi-asserted-by":"publisher","unstructured":"Liang Y, Meng F, Zhang J, Chen Y, Xu J, Zhou J (2021) An iterative multi-knowledge transfer network for aspect-based sentiment analysis. In: Findings of the association for computational linguistics: EMNLP 2021, pp 1768\u20131780. https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.152","DOI":"10.18653\/v1\/2021.findings-emnlp.152"},{"key":"11737_CR26","doi-asserted-by":"publisher","unstructured":"Chen H, Zhai Z, Feng F, Li R, Wang X (2022) Enhanced multi-channel graph convolutional network for aspect sentiment triplet extraction. In: Proceedings of the 60th annual meeting of the association for computational linguistics, vol 1: Long Papers, pp 2974\u20132985. https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.212","DOI":"10.18653\/v1\/2022.acl-long.212"},{"key":"11737_CR27","doi-asserted-by":"crossref","unstructured":"Zhang W, Deng Y, Li X, Yuan Y, Bing L, Lam W (2021) Aspect sentiment quad prediction as paraphrase generation. In: Proceedings of the 2021 conference on empirical methods in natural language processing, pp 9209\u20139219","DOI":"10.18653\/v1\/2021.emnlp-main.726"},{"key":"11737_CR28","unstructured":"Banarescu L, Bonial C, Cai S, Georgescu M, Griffitt K, Hermjakob U, Knight K, Koehn P, Palmer M, Schneider N (2013) Abstract meaning representation for sembanking. In: Proceedings of the 7th linguistic annotation workshop and interoperability with discourse, pp 178\u2013186"},{"key":"11737_CR29","doi-asserted-by":"publisher","unstructured":"Bevilacqua M, Blloshmi R, Navigli R (2021) One spring to rule them both: symmetric amr semantic parsing and generation without a complex pipeline. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 12564\u201312573. https:\/\/doi.org\/10.1609\/aaai.v35i14.17489","DOI":"10.1609\/aaai.v35i14.17489"},{"key":"11737_CR30","doi-asserted-by":"publisher","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 248\u2013255. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"11737_CR31","doi-asserted-by":"publisher","unstructured":"Liang S, Wei W, Mao X-L, Wang F, He Z (2022) Bisyn-gat+: Bi-syntax aware graph attention network for aspect-based sentiment analysis. In: Findings of the association for computational linguistics: ACL 2022, pp 1835\u20131848. https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.144","DOI":"10.18653\/v1\/2022.findings-acl.144"},{"key":"11737_CR32","doi-asserted-by":"publisher","unstructured":"Yu Y, Zhao M, Qi S-a, Sun F, Wang B, Guo W, Wang X, Yang L, Niu D (2023) Conki: contrastive knowledge injection for multimodal sentiment analysis. In: Findings of the association for computational linguistics: ACL 2023, pp 13610\u201313624. https:\/\/doi.org\/10.18653\/v1\/2023.findings-acl.860","DOI":"10.18653\/v1\/2023.findings-acl.860"},{"key":"11737_CR33","doi-asserted-by":"publisher","unstructured":"Wu H, Cheng S, Wang J, Li S, Chi L (2020) Multimodal aspect extraction with region-aware alignment network. In: Natural language processing and Chinese computing: 9th CCF International conference, NLPCC 2020, Zhengzhou, China, October 14\u201318, 2020, proceedings, Part I 9. Springer, pp 145\u2013156. https:\/\/doi.org\/10.1007\/978-3-030-60450-9_12","DOI":"10.1007\/978-3-030-60450-9_12"},{"key":"11737_CR34","doi-asserted-by":"publisher","unstructured":"Yu J, Jiang J, Yang L, Xia R (2020) Improving multimodal named entity recognition via entity span detection with unified multimodal transformer. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 3342\u20133352. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.306","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"11737_CR35","doi-asserted-by":"publisher","unstructured":"Wu Z, Zheng C, Cai Y, Chen J, Leung, H-f, Li Q (2020) Multimodal representation with embedded visual guiding objects for named entity recognition in social media posts. In: Proceedings of the 28th ACM international conference on multimedia, pp 1038\u20131046. https:\/\/doi.org\/10.1145\/3394171.3413650","DOI":"10.1145\/3394171.3413650"},{"key":"11737_CR36","doi-asserted-by":"publisher","unstructured":"Hu M, Peng Y, Huang Z, Li D, Lv Y (2019) Open-domain targeted sentiment analysis via span-based extraction and classification. In: Proceedings of the 57th annual meeting of the association for computational linguistics, pp 537\u2013546. https:\/\/doi.org\/10.18653\/v1\/P19-1051","DOI":"10.18653\/v1\/P19-1051"},{"key":"11737_CR37","doi-asserted-by":"publisher","unstructured":"Yan H, Dai J, Ji T, Qiu X, Zhang Z (2021) A unified generative framework for aspect-based sentiment analysis. In: Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing, vol 1: Long Papers, pp 2416\u20132429. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.188","DOI":"10.18653\/v1\/2021.acl-long.188"},{"key":"11737_CR38","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3345022","author":"J Mu","year":"2023","unstructured":"Mu J, Nie F, Wang W, Xu J, Zhang J, Liu H (2023) Mocolnet: a momentum contrastive learning network for multimodal aspect-level sentiment analysis. IEEE Trans Knowl Data Eng. https:\/\/doi.org\/10.1109\/TKDE.2023.3345022","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"11737_CR39","doi-asserted-by":"publisher","first-page":"102304","DOI":"10.1016\/j.inffus.2024.102304","volume":"106","author":"L Xiao","year":"2024","unstructured":"Xiao L, Wu X, Xu J, Li W, Jin C, He L (2024) Atlantis: aesthetic-oriented multiple granularities fusion network for joint multimodal aspect-based sentiment analysis. Inf Fusion 106:102304. https:\/\/doi.org\/10.1016\/j.inffus.2024.102304","journal-title":"Inf Fusion"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-025-11737-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-025-11737-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-025-11737-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T16:57:37Z","timestamp":1745427457000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-025-11737-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,6]]},"references-count":39,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["11737"],"URL":"https:\/\/doi.org\/10.1007\/s11063-025-11737-x","relation":{},"ISSN":["1573-773X"],"issn-type":[{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,6]]},"assertion":[{"value":"2 February 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 March 2025","order":2,"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 that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"25"}}