{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T11:58:19Z","timestamp":1777377499206,"version":"3.51.4"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:00:00Z","timestamp":1774396800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Array"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.array.2026.100788","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T07:08:19Z","timestamp":1775027299000},"page":"100788","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Addressing contextual sparsity in multimodal emotion recognition using speaker-focused LLM contextualization and emotion-driven augmentation"],"prefix":"10.1016","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2529-0983","authenticated-orcid":false,"given":"Aruna Gladys","family":"A.","sequence":"first","affiliation":[]},{"given":"Vetriselvi","family":"V.","sequence":"additional","affiliation":[]},{"given":"Baskar","family":"P.N.","sequence":"additional","affiliation":[]},{"given":"Arun Amaithi","family":"Rajan","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.array.2026.100788_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126693","article-title":"Survey on multimodal approaches to emotion recognition","volume":"556","author":"Aruna Gladys","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.array.2026.100788_b2","first-page":"6818","article-title":"DialogueRNN: An attentive RNN for emotion detection in conversations","volume":"33","author":"Majumder","year":"2019","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"10.1016\/j.array.2026.100788_b3","series-title":"DialogueGCN: A graph convolutional neural network for emotion recognition in conversation","author":"Ghosal","year":"2019"},{"key":"10.1016\/j.array.2026.100788_b4","series-title":"DialogueLLM: Context and emotion knowledge-tuned large language models for emotion recognition in conversations","author":"Zhang","year":"2023"},{"key":"10.1016\/j.array.2026.100788_b5","series-title":"Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (volume 1: long papers)","first-page":"7042","article-title":"DialogueCRN: Contextual reasoning networks for emotion recognition in conversations","author":"Hu","year":"2021"},{"key":"10.1016\/j.array.2026.100788_b6","series-title":"Proceedings of the 2022 conference of the North American chapter of the association for computational linguistics: human language technologies","first-page":"5669","article-title":"CoMPM: Context modeling with speaker\u2019s pre-trained memory tracking for emotion recognition in conversation","author":"Lee","year":"2022"},{"key":"10.1016\/j.array.2026.100788_b7","series-title":"Findings of the association for computational linguistics: EMNLP 2020","first-page":"2470","article-title":"COSMIC: COmmonsense knowledge for eMotion identification in conversations","author":"Ghosal","year":"2020"},{"key":"10.1016\/j.array.2026.100788_b8","series-title":"InstructERC: Reforming emotion recognition in conversation with a retrieval multi-task LLMs framework","author":"Lei","year":"2023"},{"key":"10.1016\/j.array.2026.100788_b9","series-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"10.1016\/j.array.2026.100788_b10","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1016\/j.ins.2022.08.003","article-title":"ConGNN: Context-consistent cross-graph neural network for group emotion recognition in the wild","volume":"610","author":"Wang","year":"2022","journal-title":"Inform Sci"},{"issue":"4","key":"10.1016\/j.array.2026.100788_b11","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1007\/s13735-024-00347-3","article-title":"Multi-modal emotion recognition using tensor decomposition fusion and self-supervised multi-tasking","volume":"13","author":"Wang","year":"2024","journal-title":"Int J Multimed Inf Retr"},{"key":"10.1016\/j.array.2026.100788_b12","first-page":"1","article-title":"CIME: Contextual interaction-based multimodal emotion analysis with enhanced semantic information","author":"Wang","year":"2025","journal-title":"IEEE Trans Comput Soc Syst"},{"issue":"18","key":"10.1016\/j.array.2026.100788_b13","doi-asserted-by":"crossref","first-page":"56039","DOI":"10.1007\/s11042-023-17347-w","article-title":"Emotion recognition based on brain-like multimodal hierarchical perception","volume":"83","author":"Zhu","year":"2024","journal-title":"Multimedia Tools Appl"},{"key":"10.1016\/j.array.2026.100788_b14","doi-asserted-by":"crossref","unstructured":"Zhao Y, Cambria E, E X, Zhu X. TEMPO: Training-time Equilibration of Modalities for Per-sample Optimization in Multimodal Sentiment. IEEE Trans Affect Comput 1949-3045(01):1\u201317. http:\/\/dx.doi.org\/10.1109\/TAFFC.2026.3657064, (5555) URL https:\/\/doi.ieeecomputersociety.org\/10.1109\/TAFFC.2026.3657064.","DOI":"10.1109\/TAFFC.2026.3657064"},{"key":"10.1016\/j.array.2026.100788_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.array.2025.100445","article-title":"RAFT: Robust adversarial fusion transformer for multimodal sentiment analysis","volume":"27","author":"Wang","year":"2025","journal-title":"Array"},{"key":"10.1016\/j.array.2026.100788_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103268","article-title":"RMER-DT: Robust multimodal emotion recognition in conversational contexts based on diffusion and transformers","volume":"123","author":"Zhu","year":"2025","journal-title":"Inf Fusion"},{"key":"10.1016\/j.array.2026.100788_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2024.111553","article-title":"Sentiment analysis on a low-resource language dataset using multimodal representation learning and cross-lingual transfer learning","volume":"157","author":"A.","year":"2024","journal-title":"Appl Soft Comput"},{"key":"10.1016\/j.array.2026.100788_b18","series-title":"Proceedings of the thirteenth language resources and evaluation conference","first-page":"4114","article-title":"Data augmentation with paraphrase generation and entity extraction for multimodal dialogue system","author":"Okur","year":"2022"},{"key":"10.1016\/j.array.2026.100788_b19","article-title":"TokenMix: Rethinking token mixing for multimodal sentiment analysis","author":"Zhao","year":"2023","journal-title":"IEEE Trans Multimed"},{"key":"10.1016\/j.array.2026.100788_b20","series-title":"Proceedings of the 13th workshop on computational approaches to subjectivity, sentiment, & social media analysis","first-page":"58","article-title":"Emotion and sentiment guided paraphrasing","author":"Xie","year":"2023"},{"key":"10.1016\/j.array.2026.100788_b21","series-title":"Proceedings of interspeech 2018","first-page":"2018","article-title":"Expressive neural text-to-speech synthesis with style control and transfer","author":"Wang","year":"2018"},{"key":"10.1016\/j.array.2026.100788_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103809","article-title":"Integrating audio\u2013visual text generation with contrastive learning for enhanced multimodal emotion analysis","volume":"127","author":"Xiang","year":"2026","journal-title":"Inf Fusion"},{"key":"10.1016\/j.array.2026.100788_b23","doi-asserted-by":"crossref","first-page":"1010","DOI":"10.1016\/j.procs.2024.10.329","article-title":"Abstractive english document summarization using BART model with chunk method","volume":"245","author":"Wilman","year":"2024","journal-title":"Procedia Comput Sci"},{"key":"10.1016\/j.array.2026.100788_b24","series-title":"Proceedings of the fourth ACM international conference on AI in finance","first-page":"365","article-title":"Fine-tuning pretrained language models to enhance dialogue summarization in customer service centers","author":"Yun","year":"2023"},{"key":"10.1016\/j.array.2026.100788_b25","series-title":"Mixtral of experts","author":"Jiang","year":"2024"},{"key":"10.1016\/j.array.2026.100788_b26","series-title":"ICASSP 2020 - 2020 IEEE international conference on acoustics, speech and signal processing","first-page":"6189","article-title":"Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens","author":"Valle","year":"2020"},{"issue":"4","key":"10.1016\/j.array.2026.100788_b27","doi-asserted-by":"crossref","first-page":"1917","DOI":"10.1121\/1.1458024","article-title":"YIN, a fundamental frequency estimator for speech and music","volume":"111","author":"de Cheveign\u00c3o\u0327pyright","year":"2002","journal-title":"J Acoust Soc Am"},{"key":"10.1016\/j.array.2026.100788_b28","series-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"Wang","year":"2018"},{"key":"10.1016\/j.array.2026.100788_b29","series-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"Kong","year":"2020"},{"key":"10.1016\/j.array.2026.100788_b30","series-title":"Advances in neural information processing systems (neurIPS 2020)","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"10.1016\/j.array.2026.100788_b31","series-title":"Proceedings of the 57th annual meeting of the association for computational linguistics","first-page":"527","article-title":"MELD: A multimodal multi-party dataset for emotion recognition in conversations","author":"Poria","year":"2019"},{"key":"10.1016\/j.array.2026.100788_b32","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.array.2026.100788_b33","series-title":"Emotion detection on TV show transcripts with sequence-based convolutional neural networks","author":"Zahiri","year":"2017"},{"key":"10.1016\/j.array.2026.100788_b34","series-title":"Emotion english DistilRoBERTa-base","author":"Hartmann","year":"2022"},{"key":"10.1016\/j.array.2026.100788_b35","series-title":"Proceedings of the 2018 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long papers)","first-page":"2122","article-title":"Conversational memory network for emotion recognition in dyadic dialogue videos","author":"Hazarika","year":"2018"},{"key":"10.1016\/j.array.2026.100788_b36","series-title":"DialogXL: All-in-one XLNet for multi-party conversation emotion recognition","author":"Shen","year":"2020"},{"key":"10.1016\/j.array.2026.100788_b37","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1016\/j.neucom.2022.06.072","article-title":"Conversational emotion recognition studies based on graph convolutional neural networks and a dependent syntactic analysis","volume":"501","author":"Shou","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.array.2026.100788_b38","series-title":"Efficient long-distance latent relation-aware graph neural network for multi-modal emotion recognition in conversations","author":"Shou","year":"2024"},{"issue":"2","key":"10.1016\/j.array.2026.100788_b39","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1109\/TAFFC.2023.3280038","article-title":"Disentangled variational autoencoder for emotion recognition in conversations","volume":"15","author":"Yang","year":"2024","journal-title":"IEEE Trans Affect Comput"},{"key":"10.1016\/j.array.2026.100788_b40","series-title":"Proceedings of the 2024 joint international conference on computational linguistics, language resources and evaluation","first-page":"5711","article-title":"Emotion recognition in conversation via dynamic personality","author":"Wang","year":"2024"}],"container-title":["Array"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2590005626001116?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2590005626001116?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T09:07:46Z","timestamp":1777367266000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2590005626001116"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":40,"alternative-id":["S2590005626001116"],"URL":"https:\/\/doi.org\/10.1016\/j.array.2026.100788","relation":{},"ISSN":["2590-0056"],"issn-type":[{"value":"2590-0056","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Addressing contextual sparsity in multimodal emotion recognition using speaker-focused LLM contextualization and emotion-driven augmentation","name":"articletitle","label":"Article Title"},{"value":"Array","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.array.2026.100788","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 Inc.","name":"copyright","label":"Copyright"}],"article-number":"100788"}}