{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T12:03:57Z","timestamp":1781006637689,"version":"3.54.1"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.116044","type":"journal-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:42:08Z","timestamp":1777131728000},"page":"116044","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MoWER: Multimodal emotion recognition in conversation with emotion wheel-enhanced representation"],"prefix":"10.1016","volume":"345","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2987-7311","authenticated-orcid":false,"given":"Jing","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0741-0538","authenticated-orcid":false,"given":"Jingwen","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5301-5767","authenticated-orcid":false,"given":"Mingjian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4253-9006","authenticated-orcid":false,"given":"Yuanhui","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6969-0562","authenticated-orcid":false,"given":"Yan","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116044_b1","series-title":"Large language models in mental health care: a scoping review","author":"Hua","year":"2024"},{"issue":"3","key":"10.1016\/j.knosys.2026.116044_b2","doi-asserted-by":"crossref","first-page":"220","DOI":"10.3390\/brainsci15030220","article-title":"From neural networks to emotional networks: A systematic review of EEG-based emotion recognition in cognitive neuroscience and real-world applications","volume":"15","author":"Gkintoni","year":"2025","journal-title":"Brain Sci."},{"key":"10.1016\/j.knosys.2026.116044_b3","series-title":"Large language models in mental health care: a scoping review","author":"Hua","year":"2024"},{"key":"10.1016\/j.knosys.2026.116044_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113601","article-title":"Multi-views emotional knowledge extraction for emotion recognition in conversation","author":"Jian","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116044_b5","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"6818","article-title":"Dialoguernn: An attentive rnn for emotion detection in conversations","volume":"vol. 33","author":"Majumder","year":"2019"},{"key":"10.1016\/j.knosys.2026.116044_b6","series-title":"Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation","author":"Ghosal","year":"2019"},{"key":"10.1016\/j.knosys.2026.116044_b7","series-title":"Dialoguetrm: Exploring the intra-and inter-modal emotional behaviors in the conversation","author":"Mao","year":"2020"},{"key":"10.1016\/j.knosys.2026.116044_b8","article-title":"Der-gcn: Dialog and event relation-aware graph convolutional neural network for multimodal dialog emotion recognition","author":"Ai","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116044_b9","series-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"7037","article-title":"MM-DFN: Multimodal dynamic fusion network for emotion recognition in conversations","author":"Hu","year":"2022"},{"key":"10.1016\/j.knosys.2026.116044_b10","series-title":"MMGCN: Multimodal fusion via deep graph convolution network for emotion recognition in conversation","author":"Hu","year":"2021"},{"key":"10.1016\/j.knosys.2026.116044_b11","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"19089","article-title":"Adaptive graph learning for multimodal conversational emotion detection","volume":"vol. 38","author":"Tu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116044_b12","series-title":"Supervised adversarial contrastive learning for emotion recognition in conversations","author":"Hu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116044_b13","article-title":"An approachto environmental psychology, Cambridge, MA: Mitpress","author":"Mehrabian","year":"1974","journal-title":"MehrabianAn Approach To Environ. Psychol."},{"key":"10.1016\/j.knosys.2026.116044_b14","series-title":"Emotion-anchored contrastive learning framework for emotion recognition in conversation","author":"Yu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116044_b15","series-title":"Emotion: a psychoevolutionary synthesis","author":"Camras","year":"1980"},{"key":"10.1016\/j.knosys.2026.116044_b16","series-title":"Enhancing cognitive models of emotions with representation learning","author":"Guo","year":"2021"},{"key":"10.1016\/j.knosys.2026.116044_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111954","article-title":"Multi-modal graph context extraction and consensus-aware learning for emotion recognition in conversation","volume":"298","author":"Dai","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116044_b18","article-title":"Disentangled variational autoencoder for emotion recognition in conversations","author":"Yang","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2026.116044_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110794","article-title":"A survey of dialogic emotion analysis: Developments, approaches and perspectives","author":"Gan","year":"2024","journal-title":"Pattern Recognit."},{"issue":"1","key":"10.1016\/j.knosys.2026.116044_b20","first-page":"1","article-title":"Deep emotion recognition in textual conversations: A survey","volume":"58","author":"Pereira","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.knosys.2026.116044_b21","series-title":"CoMPM: Context modeling with speaker\u2019s pre-trained memory tracking for emotion recognition in conversation","author":"Lee","year":"2021"},{"key":"10.1016\/j.knosys.2026.116044_b22","doi-asserted-by":"crossref","DOI":"10.1109\/TAFFC.2025.3537538","article-title":"Linecongraphs: Line conversation graphs for effective emotion recognition using graph neural networks","author":"Krishnan","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2026.116044_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.108861","article-title":"Emotion recognition in conversations with emotion shift detection based on multi-task learning","volume":"248","author":"Gao","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116044_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108339","article-title":"Using transformers for multimodal emotion recognition: Taxonomies and state of the art review","volume":"133","author":"Hazmoune","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116044_b25","series-title":"Multimodal emotion recognition and sentiment analysis in multi-party conversation contexts","author":"Farhadipour","year":"2025"},{"key":"10.1016\/j.knosys.2026.116044_b26","series-title":"Proceedings of the Conference. Association for Computational Linguistics. Meeting","first-page":"6558","article-title":"Multimodal transformer for unaligned multimodal language sequences","volume":"vol. 2019","author":"Tsai","year":"2019"},{"key":"10.1016\/j.knosys.2026.116044_b27","doi-asserted-by":"crossref","unstructured":"D. Hazarika, R. Zimmermann, S. Poria, Misa: Modality-invariant and-specific representations for multimodal sentiment analysis, in: Proceedings of the 28th ACM International Conference on Multimedia, 2020, pp. 1122\u20131131.","DOI":"10.1145\/3394171.3413678"},{"key":"10.1016\/j.knosys.2026.116044_b28","series-title":"BeMERC: Behavior-aware MLLM-based framework for multimodal emotion recognition in conversation","author":"Fu","year":"2025"},{"key":"10.1016\/j.knosys.2026.116044_b29","article-title":"A transformer-based model with self-distillation for multimodal emotion recognition in conversations","author":"Ma","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116044_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111969","article-title":"Speaker-aware cognitive network with cross-modal attention for multimodal emotion recognition in conversation","volume":"296","author":"Guo","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116044_b31","series-title":"Der-gcn: Dialogue and event relation-aware graph convolutional neural network for multimodal dialogue emotion recognition","author":"Ai","year":"2023"},{"key":"10.1016\/j.knosys.2026.116044_b32","doi-asserted-by":"crossref","unstructured":"D. Zhang, F. Chen, X. Chen, Dualgats: Dual graph attention networks for emotion recognition in conversations, in: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023, pp. 7395\u20137408.","DOI":"10.18653\/v1\/2023.acl-long.408"},{"key":"10.1016\/j.knosys.2026.116044_b33","series-title":"Curriculum learning meets directed acyclic graph for multimodal emotion recognition","author":"Nguyen","year":"2024"},{"key":"10.1016\/j.knosys.2026.116044_b34","series-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","first-page":"2947","article-title":"CEPT: A contrast-enhanced prompt-tuning framework for emotion recognition in conversation","author":"Gao","year":"2024"},{"key":"10.1016\/j.knosys.2026.116044_b35","doi-asserted-by":"crossref","first-page":"3292","DOI":"10.1109\/TASLPRO.2025.3592325","article-title":"Knowledge-enhanced prompt-tuning with contrastive learning for emotion recognition in conversations","volume":"33","author":"Gao","year":"2025","journal-title":"IEEE Trans. Audio, Speech Lang. Process."},{"key":"10.1016\/j.knosys.2026.116044_b36","series-title":"Visual prompting in llms for enhancing emotion recognition","author":"Zhang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116044_b37","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2025.3588892","article-title":"Visual and textual prompts in vllms for enhancing emotion recognition","author":"Wang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.116044_b38","unstructured":"C. He, S. Zhu, H. Liu, F. Gao, Y. Jia, H. Zan, M. Peng, DialogueMMT: Dialogue Scenes Understanding Enhanced Multi-modal Multi-task Tuning for Emotion Recognition in Conversations, in: Proceedings of the 31st International Conference on Computational Linguistics, 2025, pp. 2497\u20132512."},{"key":"10.1016\/j.knosys.2026.116044_b39","doi-asserted-by":"crossref","unstructured":"J. Lee, Y. Jang, H. Kim, W. Lee, H. Kim, Analyzing key factors influencing emotion prediction performance of vllms in conversational contexts, in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024, pp. 5801\u20135816.","DOI":"10.18653\/v1\/2024.emnlp-main.331"},{"key":"10.1016\/j.knosys.2026.116044_b40","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128196","article-title":"Htnet for micro-expression recognition","volume":"602","author":"Wang","year":"2024","journal-title":"Neurocomputing"},{"issue":"28","key":"10.1016\/j.knosys.2026.116044_b41","doi-asserted-by":"crossref","first-page":"43251","DOI":"10.1007\/s11042-023-14885-1","article-title":"Affect-GCN: a multimodal graph convolutional network for multi-emotion with intensity recognition and sentiment analysis in dialogues","volume":"82","author":"Firdaus","year":"2023","journal-title":"Multimedia Tools Appl."},{"issue":"140","key":"10.1016\/j.knosys.2026.116044_b42","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.knosys.2026.116044_b43","doi-asserted-by":"crossref","unstructured":"F. Eyben, M. W\u00f6llmer, B. Schuller, Opensmile: the munich versatile and fast open-source audio feature extractor, in: Proceedings of the 18th ACM International Conference on Multimedia, 2010, pp. 1459\u20131462.","DOI":"10.1145\/1873951.1874246"},{"key":"10.1016\/j.knosys.2026.116044_b44","doi-asserted-by":"crossref","unstructured":"J. Carreira, A. Zisserman, Quo vadis, action recognition? a new model and the kinetics dataset, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 6299\u20136308.","DOI":"10.1109\/CVPR.2017.502"},{"key":"10.1016\/j.knosys.2026.116044_b45","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"IEMOCAP: Interactive emotional dyadic motion capture database","volume":"42","author":"Busso","year":"2008","journal-title":"Lang. Resour. Eval."},{"key":"10.1016\/j.knosys.2026.116044_b46","series-title":"Meld: A multimodal multi-party dataset for emotion recognition in conversations","author":"Poria","year":"2018"},{"key":"10.1016\/j.knosys.2026.116044_b47","series-title":"Proceedings of the Conference. Association for Computational Linguistics. North American Chapter. Meeting","first-page":"2122","article-title":"Conversational memory network for emotion recognition in dyadic dialogue videos","volume":"vol. 2018","author":"Hazarika","year":"2018"},{"key":"10.1016\/j.knosys.2026.116044_b48","doi-asserted-by":"crossref","unstructured":"D. Hazarika, S. Poria, R. Mihalcea, E. Cambria, R. Zimmermann, Icon: Interactive conversational memory network for multimodal emotion detection, in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018, pp. 2594\u20132604.","DOI":"10.18653\/v1\/D18-1280"},{"key":"10.1016\/j.knosys.2026.116044_b49","doi-asserted-by":"crossref","first-page":"4422","DOI":"10.1109\/TMM.2021.3117062","article-title":"LR-GCN: Latent relation-aware graph convolutional network for conversational emotion recognition","volume":"24","author":"Ren","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116044_b50","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Enhanced multimodal emotion recognition in conversations via contextual filtering and multi-frequency graph propagation","author":"Zhao","year":"2025"},{"key":"10.1016\/j.knosys.2026.116044_b51","unstructured":"Y. Shou, T. Meng, W. Ai, K. Li, Dynamic Graph Neural ODE Network for Multi-modal Emotion Recognition in Conversation, in: Proceedings of the 31st International Conference on Computational Linguistics, 2025, pp. 256\u2013268."},{"key":"10.1016\/j.knosys.2026.116044_b52","doi-asserted-by":"crossref","first-page":"776","DOI":"10.1109\/TMM.2023.3271019","article-title":"A transformer-based model with self-distillation for multimodal emotion recognition in conversations","volume":"26","author":"Ma","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116044_b53","series-title":"Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing","author":"He","year":"2021"},{"key":"10.1016\/j.knosys.2026.116044_b54","series-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126007707?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126007707?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T11:34:37Z","timestamp":1781004877000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126007707"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":54,"alternative-id":["S0950705126007707"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116044","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MoWER: Multimodal emotion recognition in conversation with emotion wheel-enhanced representation","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116044","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116044"}}